© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 40833
    Prev
    Next
    INDEX
    Explanations

    instances of the word "yet"

    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
    +0.10
    0.5%
    93
    +0.09
    0.4%
    652
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    291
    +0.10
    0.09
    393
    +0.09
    0.20
    527
    +0.08
    0.02
    Negative Logits
    rities
    -0.74
    stories
    -0.64
    equality
    -0.61
    gnu
    -0.59
    tein
    -0.58
     Journals
    -0.57
    ï
    -0.57
    warts
    -0.56
    =#
    -0.55
     Traps
    -0.55
    POSITIVE LOGITS
     TBD
    0.65
    uden
    0.63
    YY
    0.62
     surpassed
    0.61
    icia
    0.58
    bra
    0.57
     officially
    0.57
     definitively
    0.56
    ijn
    0.56
    yy
    0.56
    Activations Density 8.178%

    No Known Activations