Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 4225
    Prev
    Next
    INDEX
    Explanations

    distances expressed in kilometers

    oai_token-act-pair · gpt-3.5-turbo

    quantities and units of measurement

    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
     Osw
    -0.82
     Pot
    -0.71
     IF
    -0.69
     TODAY
    -0.65
     steroids
    -0.64
     Bubble
    -0.63
     THEN
    -0.62
     Firefly
    -0.62
     Bot
    -0.62
     XIII
    -0.60
    POSITIVE LOGITS
    ortal
    0.99
    wagen
    0.98
    rpm
    0.97
    ature
    0.96
    ooth
    0.95
    endment
    0.95
    km
    0.94
    obiles
    0.92
    axy
    0.92
    obile
    0.92
    Activations Density 0.007%

    No Known Activations