© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 32989
    Prev
    Next
    INDEX
    Explanations

    technical terms related to electronic devices or systems

    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
    745
    +0.14
    0.7%
    414
    +0.10
    0.5%
    726
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    701
    +0.14
    0.08
    726
    +0.10
    0.10
    247
    +0.09
    0.07
    Negative Logits
     Seym
    -0.61
    kefeller
    -0.56
    ktop
    -0.55
     congratulations
    -0.55
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.54
    anmar
    -0.54
     Congratulations
    -0.53
    ã쮿
    -0.53
    âĢ¢âĢ¢
    -0.51
    $$$$
    -0.51
    POSITIVE LOGITS
    ted
    0.82
    ting
    0.76
    nation
    0.73
    rent
    0.68
    ches
    0.66
    ipl
    0.64
    station
    0.64
    age
    0.62
    chers
    0.61
    illance
    0.60
    Activations Density 7.900%

    No Known Activations