© 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. 39906
    Prev
    Next
    INDEX
    Explanations

    players and statistics related to American football

    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
    527
    +0.12
    0.7%
    288
    +0.08
    0.5%
    162
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    162
    +0.12
    0.04
    435
    +0.08
    0.02
    668
    +0.07
    0.03
    Negative Logits
    henko
    -0.60
    SHIP
    -0.58
    PsyNetMessage
    -0.56
    amera
    -0.56
    ickr
    -0.55
    zers
    -0.53
    ngth
    -0.53
    etsk
    -0.52
    awaru
    -0.51
    byn
    -0.51
    POSITIVE LOGITS
     Patriots
    0.82
    ers
    0.66
     Meadow
    0.61
     Armory
    0.57
    ica
    0.57
     Bay
    0.56
     Revolution
    0.56
     Garden
    0.55
     Patriot
    0.54
     Tea
    0.52
    Activations Density 6.735%

    No Known Activations