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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 40332
    Prev
    Next
    INDEX
    Explanations

    words related to headwear, specifically hats

    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
    7
    +0.15
    0.6%
    526
    +0.12
    0.5%
    260
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.15
    0.15
    386
    +0.12
    0.08
    260
    +0.12
    0.08
    Negative Logits
     MSM
    -0.80
     Integ
    -0.79
    theless
    -0.77
     Ong
    -0.75
    uality
    -0.74
    ateral
    -0.73
     Borders
    -0.72
     CLS
    -0.71
     Impossible
    -0.69
     Diagn
    -0.68
    POSITIVE LOGITS
    chet
    1.75
    chery
    1.58
    ches
    1.24
     brim
    1.20
    cher
    1.15
    glers
    1.14
    eless
    1.10
     hat
    1.07
     hats
    1.05
    pin
    1.04
    Activations Density 4.502%

    No Known Activations