© 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. 34740
    Prev
    Next
    INDEX
    Explanations

    technical terms or phrases related to different options or choices in a discussion or situation

    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
    +0.30
    1.5%
    754
    +0.13
    0.6%
    101
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    596
    +0.30
    0.07
    435
    +0.13
    0.03
    109
    +0.12
    0.06
    Negative Logits
    urst
    -0.73
    soever
    -0.69
    hemat
    -0.69
    mind
    -0.68
    rollers
    -0.65
    ritic
    -0.64
    orks
    -0.64
    itizens
    -0.63
    ãĥĥãĥī
    -0.62
    tub
    -0.62
    POSITIVE LOGITS
     options
    0.95
     option
    0.83
    finder
    0.79
    atives
    0.78
     choices
    0.74
     Option
    0.69
     Altern
    0.69
    rison
    0.68
     choice
    0.68
    Option
    0.67
    Activations Density 6.077%

    No Known Activations