© 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. 13158
    Prev
    Next
    INDEX
    Explanations

    web links, numbers, and metadata references within texts

    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
    +0.15
    0.7%
    7
    +0.11
    0.5%
    236
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.15
    0.18
    488
    +0.11
    0.11
    11
    +0.10
    0.07
    Negative Logits
    istically
    -0.83
    think
    -0.75
    holder
    -0.72
    ously
    -0.70
    estine
    -0.69
    blind
    -0.65
    bro
    -0.65
    journal
    -0.63
    athing
    -0.63
    ige
    -0.63
    POSITIVE LOGITS
     ILCS
    0.92
    é¾
    0.79
     dB
    0.76
    374
    0.74
    artment
    0.74
    508
    0.70
    20439
    0.68
    UTERS
    0.67
    503
    0.66
    mph
    0.66
    Activations Density 5.960%

    No Known Activations