Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 4386
    Prev
    Next
    INDEX
    Explanations

    timestamps and usernames in a chat or social media conversation

    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
    640
    +0.13
    0.6%
    132
    +0.11
    0.5%
    523
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.13
    0.19
    393
    +0.11
    0.20
    632
    +0.11
    0.05
    Negative Logits
    bably
    -0.90
    ģ«
    -0.85
    ©¶æ
    -0.84
    xtap
    -0.81
    ĪĴ
    -0.76
    İĭ
    -0.72
    ¥ŀ
    -0.72
    £
    -0.70
    ©¶æ¥µ
    -0.70
     corrid
    -0.69
    POSITIVE LOGITS
    EMOTE
    0.78
     VIEW
    0.77
     xp
    0.76
    SAY
    0.73
     DEBUG
    0.71
     CLIENT
    0.69
     Kad
    0.65
     <@
    0.64
    wolves
    0.63
    EY
    0.63
    Activations Density 7.613%

    No Known Activations