© 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. 8-RES-JB
    11. 9049
    Prev
    Next
    INDEX
    Explanations

    references to the phrase "nail" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "nail" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inventoryQuantity
    -0.86
    ais
    -0.74
    REDACTED
    -0.73
    ouls
    -0.73
    ioch
    -0.73
    overe
    -0.71
    ivia
    -0.70
    =-=-=-=-=-=-=-=-
    -0.69
    Æ
    -0.68
    ivals
    -0.66
    POSITIVE LOGITS
     polish
    1.16
     nail
    1.11
     nails
    1.08
     salon
    1.00
     biting
    0.93
     fungus
    0.83
    picking
    0.82
     coffin
    0.82
     nailed
    0.79
     groom
    0.77
    Activations Density 0.053%

    No Known Activations