© 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. 3-RES-JB
    11. 1708
    Prev
    Next
    INDEX
    Explanations

    references to fingers and actions related to fingers

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "finger" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tics
    -0.78
    igslist
    -0.78
    ean
    -0.73
    xual
    -0.71
    supp
    -0.67
    liga
    -0.65
    sent
    -0.64
    yahoo
    -0.64
    come
    -0.64
     Equality
    -0.63
    POSITIVE LOGITS
     finger
    1.15
     fingers
    0.99
     nail
    0.97
    picking
    0.95
     Finger
    0.93
     nails
    0.93
    finger
    0.85
     lick
    0.84
    pointer
    0.84
     swipe
    0.83
    Activations Density 0.008%

    No Known Activations