© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 32881
    Prev
    Next
    INDEX
    Explanations

    information related to computer programming and technical processes, including initialization of components and processes, handling of data, technical constraints, and computational optimization

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.30
    1.4%
    33
    +0.11
    0.5%
    411
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    481
    +0.30
    0.28
    288
    +0.11
    0.27
    255
    +0.11
    0.11
    Negative Logits
    cffffcc
    -0.96
    ãĤ´ãĥ³
    -0.69
    ĪĴ
    -0.68
    aukee
    -0.61
    regon
    -0.59
    hement
    -0.57
    iland
    -0.57
    utics
    -0.57
     âĵĺ
    -0.57
    enture
    -0.56
    POSITIVE LOGITS
     required
    0.81
     needed
    0.79
     per
    0.78
     varies
    0.77
     involved
    0.76
     necessary
    0.71
     consumed
    0.69
     available
    0.69
    verage
    0.68
    levant
    0.67
    Activations Density 15.833%

    No Known Activations