© 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. 14042
    Prev
    Next
    INDEX
    Explanations

    file paths or directories in a specific format

    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
    496
    +0.12
    0.6%
    284
    +0.10
    0.5%
    625
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.12
    0.14
    730
    +0.10
    0.07
    683
    +0.10
    0.05
    Negative Logits
    âĹ¼
    -0.75
    Gy
    -0.71
    meat
    -0.68
    manship
    -0.68
     Qian
    -0.64
    phal
    -0.61
     Hes
    -0.60
    assic
    -0.60
     Halls
    -0.59
     Referred
    -0.58
    POSITIVE LOGITS
    urable
    0.79
    etc
    0.79
    maxwell
    0.79
     decomp
    0.76
    obar
    0.76
    uration
    0.74
    ogle
    0.71
    config
    0.71
    idences
    0.69
    enhagen
    0.69
    Activations Density 3.477%

    No Known Activations