© 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. 3990
    Prev
    Next
    INDEX
    Explanations

    proper nouns

    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
    717
    +0.13
    0.6%
    728
    +0.10
    0.5%
    71
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.13
    0.35
    521
    +0.10
    0.02
    6
    +0.10
    0.17
    Negative Logits
    ĸļ
    -0.83
     veins
    -0.81
    soDeliveryDate
    -0.75
     parcels
    -0.70
    imilar
    -0.69
    onyms
    -0.69
     hus
    -0.67
     omission
    -0.66
     Cth
    -0.63
     pockets
    -0.62
    POSITIVE LOGITS
    ilot
    0.74
     Ferry
    0.70
    trial
    0.68
    vertisement
    0.67
    olesterol
    0.66
    alion
    0.65
    gain
    0.65
    ij士
    0.65
    cycles
    0.64
    amines
    0.63
    Activations Density 17.307%

    No Known Activations