© 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. 574
    Prev
    Next
    INDEX
    Explanations

    the word "vest."

    oai_token-act-pair · gpt-4-turbo

    mentions or descriptions of "vest" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to types of vests, both literal and figurative

    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
    Raw
    -0.80
    avez
    -0.71
    paces
    -0.69
    USA
    -0.69
    HCR
    -0.68
    éĹĺ
    -0.66
    thel
    -0.66
    Refer
    -0.64
    raltar
    -0.63
    figure
    -0.63
    POSITIVE LOGITS
     vest
    1.32
    ige
    1.04
    igious
    0.91
    ments
    0.89
    igation
    0.88
     curtain
    0.85
     wardrobe
    0.85
     worn
    0.84
    robe
    0.83
    ively
    0.82
    Activations Density 0.004%

    No Known Activations