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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 39961
    Prev
    Next
    INDEX
    Explanations

    information related to architectural structures and critical analysis.

    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
    314
    +0.04
    0.6%
    288
    +0.03
    0.4%
    634
    +0.03
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    767
    +0.04
    0.11
    314
    +0.03
    -0.06
    288
    +0.03
    0.24
    Negative Logits
    isSpecialOrderable
    -0.23
    claw
    -0.22
     Kimmel
    -0.21
     stride
    -0.21
     allotted
    -0.21
     Span
    -0.20
     Kills
    -0.20
     healed
    -0.20
     Immunity
    -0.20
    trial
    -0.20
    POSITIVE LOGITS
    mosp
    0.27
    itect
    0.27
    reprene
    0.27
    roleum
    0.27
    alist
    0.27
    osterone
    0.26
    itsch
    0.26
    quartered
    0.26
    ionage
    0.25
    yright
    0.25
    Activations Density 11.003%

    No Known Activations