© 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. 45921
    Prev
    Next
    INDEX
    Explanations

    code snippets related to software development and programming tasks

    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
    +0.16
    0.8%
    459
    +0.10
    0.5%
    519
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    399
    +0.16
    0.05
    137
    +0.10
    0.02
    248
    +0.10
    0.03
    Negative Logits
    leans
    -0.67
    peria
    -0.61
    osher
    -0.61
    onite
    -0.58
    Ö¼
    -0.56
    lished
    -0.56
    thal
    -0.55
     Manafort
    -0.55
    avery
    -0.55
     bribes
    -0.53
    POSITIVE LOGITS
    ctl
    0.81
    ()
    0.76
    Loop
    0.75
    Ctrl
    0.74
    tenance
    0.72
    interface
    0.71
    cmd
    0.70
    ().
    0.70
    Code
    0.69
    menu
    0.68
    Activations Density 8.991%

    No Known Activations