© 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. 3995
    Prev
    Next
    INDEX
    Explanations

    email subscription-related text strings

    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
    +0.17
    0.9%
    211
    +0.10
    0.5%
    218
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.17
    0.31
    393
    +0.10
    0.31
    283
    +0.09
    0.02
    Negative Logits
    ector
    -0.65
     redes
    -0.62
    seys
    -0.59
    iaries
    -0.56
    rats
    -0.56
     trophies
    -0.55
    phia
    -0.54
    ilts
    -0.54
    burgh
    -0.53
     Surviv
    -0.52
    POSITIVE LOGITS
     Finish
    0.60
    repeat
    0.60
    icol
    0.59
    Finish
    0.58
     Cancel
    0.54
    come
    0.54
    please
    0.54
    destruct
    0.53
    OTUS
    0.52
    push
    0.52
    Activations Density 12.620%

    No Known Activations