© 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. 13669
    Prev
    Next
    INDEX
    Explanations

    references to specific website pages or URLs

    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
    +0.15
    0.7%
    280
    +0.10
    0.4%
    253
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    253
    +0.15
    0.14
    517
    +0.10
    0.11
    245
    +0.10
    0.11
    Negative Logits
    inator
    -0.78
    ĻĤ
    -0.73
    agos
    -0.71
    ãĥ¼ãĥĨãĤ£
    -0.70
     eleph
    -0.69
    ¿½
    -0.66
     plur
    -0.65
     omn
    -0.64
     oun
    -0.63
    ª
    -0.63
    POSITIVE LOGITS
    tm
    0.77
     (*
    0.71
    Deal
    0.70
    âĢł
    0.66
    drivers
    0.66
    Madison
    0.64
    FIELD
    0.63
    20439
    0.63
    head
    0.62
    Screen
    0.62
    Activations Density 8.129%

    No Known Activations