© 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
    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. 40786
    Prev
    Next
    INDEX
    Explanations

    words related to being on top of something, whether physically or metaphorically

    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
    679
    +0.12
    0.5%
    526
    +0.12
    0.5%
    317
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    686
    +0.12
    0.04
    317
    +0.12
    0.07
    729
    +0.10
    0.06
    Negative Logits
    cci
    -0.86
    æ©Ł
    -0.78
    gged
    -0.74
    ishable
    -0.74
     Advent
    -0.72
    arij
    -0.72
    uld
    -0.71
    enegger
    -0.71
    inals
    -0.71
    encers
    -0.70
    POSITIVE LOGITS
    deck
    1.09
    most
    1.02
    retty
    0.95
    ography
    0.95
    mast
    0.89
     billing
    0.85
    model
    0.84
     tier
    0.84
     shelf
    0.84
    ĺħ
    0.83
    Activations Density 3.844%

    No Known Activations