© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 9384
    Prev
    Next
    INDEX
    Explanations

    words related to skiing

    oai_token-act-pair · gpt-3.5-turbo

    words related to skiing and associated terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     brunt
    -0.68
    icas
    -0.68
    nard
    -0.68
    ãĥ¬
    -0.67
    angered
    -0.65
    mort
    -0.64
     publicity
    -0.64
     ACTIONS
    -0.63
    spring
    -0.63
     Clintons
    -0.63
    POSITIVE LOGITS
    pping
    0.95
    inski
    0.93
    pper
    0.92
    ety
    0.92
    zzi
    0.92
    owski
    0.91
    y
    0.89
    arity
    0.87
    qi
    0.86
    ski
    0.86
    Activations Density 0.009%

    No Known Activations