© 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. 33884
    Prev
    Next
    INDEX
    Explanations

    mentions of products or items being evaluated or discussed in detail

    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
    +0.20
    1.5%
    393
    +0.13
    1.0%
    712
    +0.07
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.20
    0.31
    385
    +0.13
    0.19
    362
    +0.07
    0.15
    Negative Logits
    cade
    -0.42
    earchers
    -0.40
    wig
    -0.39
    head
    -0.37
    ppa
    -0.37
     Unsure
    -0.37
    uations
    -0.36
    uyomi
    -0.36
    oiler
    -0.35
    bang
    -0.35
    POSITIVE LOGITS
     ours
    0.58
     sorts
    0.57
     theirs
    0.49
     hers
    0.49
     everyday
    0.45
     mine
    0.43
     humanity
    0.41
     yours
    0.41
     virtue
    0.40
     bip
    0.40
    Activations Density 12.216%

    No Known Activations