© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 3133
    Prev
    Next
    INDEX
    Explanations

    references to fingers being involved in various activities or situations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "fingers" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     [|
    -0.73
    judicial
    -0.71
    nz
    -0.70
    vez
    -0.69
     Medic
    -0.67
    houses
    -0.66
    spect
    -0.63
     Spe
    -0.62
    house
    -0.62
    json
    -0.62
    POSITIVE LOGITS
     fingers
    1.33
    ingers
    1.15
    pring
    1.13
     finger
    0.98
     fingertips
    0.94
     thumb
    0.88
    finger
    0.88
     prick
    0.86
    creen
    0.85
    uckles
    0.85
    Activations Density 0.007%

    No Known Activations