© 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. 13003
    Prev
    Next
    INDEX
    Explanations

    references to the word "Wool"

    oai_token-act-pair · gpt-3.5-turbo

    references to wool

    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
     Aval
    -0.70
     Explain
    -0.69
     Hiroshima
    -0.68
     citation
    -0.67
     Oro
    -0.65
    CENT
    -0.65
     Cuomo
    -0.63
     INF
    -0.63
     Referred
    -0.62
     Activate
    -0.62
    POSITIVE LOGITS
    wich
    1.16
    sey
    1.08
    worth
    1.07
    wyn
    1.03
    awei
    1.02
    nesday
    0.97
    enn
    0.96
    worms
    0.96
    igan
    0.95
    isine
    0.94
    Activations Density 0.004%

    No Known Activations