© 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. 39835
    Prev
    Next
    INDEX
    Explanations

    information related to sports teams and transactions

    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
    +0.13
    0.6%
    75
    +0.11
    0.5%
    538
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.13
    0.18
    738
    +0.11
    0.08
    105
    +0.10
    0.10
    Negative Logits
    ago
    -0.72
    ELD
    -0.70
    éĹ
    -0.68
    otten
    -0.66
    à¨
    -0.66
    inished
    -0.66
    lied
    -0.63
    BuyableInstoreAndOnline
    -0.62
    Downloadha
    -0.61
    quartered
    -0.61
    POSITIVE LOGITS
     ourselves
    0.88
    querade
    0.73
     hypot
    0.66
     clarify
    0.65
    joice
    0.63
     rg
    0.60
     REAL
    0.59
     together
    0.59
    dule
    0.58
     Friendship
    0.58
    Activations Density 14.397%

    No Known Activations