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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 36816
    Prev
    Next
    INDEX
    Explanations

    words related to a specific card game, potentially focusing on cards, strategies, and in-game actions

    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
    +0.22
    1.1%
    481
    +0.13
    0.6%
    552
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.22
    0.15
    326
    +0.13
    0.39
    232
    +0.08
    0.12
    Negative Logits
     unpop
    -0.71
     graded
    -0.64
     populated
    -0.63
     stocked
    -0.63
     branch
    -0.61
     reclaimed
    -0.61
     endowed
    -0.58
     stocking
    -0.56
     enrolled
    -0.56
     refurb
    -0.56
    POSITIVE LOGITS
    ingly
    1.06
    ings
    0.89
    ing
    0.86
    ting
    0.83
    fulness
    0.81
    eful
    0.80
    INGS
    0.78
    eworthy
    0.76
    words
    0.76
    !,
    0.75
    Activations Density 25.352%

    No Known Activations