© 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. 4084
    Prev
    Next
    INDEX
    Explanations

    historical and informational text

    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
    +0.14
    0.6%
    195
    +0.13
    0.5%
    503
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    568
    +0.14
    0.06
    288
    +0.13
    0.15
    701
    +0.11
    0.06
    Negative Logits
    FUL
    -0.97
    LESS
    -0.83
     Pru
    -0.81
    hips
    -0.77
    folk
    -0.73
    holding
    -0.73
     humming
    -0.70
    ÙIJ
    -0.69
    WARE
    -0.69
    ARDS
    -0.68
    POSITIVE LOGITS
    iphany
    1.56
    iscopal
    1.36
    istle
    1.34
    hemer
    1.31
    isodes
    1.23
    idem
    1.11
    onymous
    1.10
    iph
    1.07
    igen
    1.04
    isc
    1.03
    Activations Density 4.867%

    No Known Activations