© 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. 8327
    Prev
    Next
    INDEX
    Explanations

    references to the region or province "BC" (British Columbia)

    oai_token-act-pair · gpt-3.5-turbo
    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
    mble
    -1.12
    lihood
    -0.82
    ktop
    -0.80
    ãĤ¯
    -0.80
    geant
    -0.76
    hower
    -0.72
    ppings
    -0.72
     "\
    -0.70
    geist
    -0.69
    velt
    -0.67
    POSITIVE LOGITS
     BC
    0.89
    ategory
    0.81
    BG
    0.81
    AMP
    0.76
     NDP
    0.76
    orne
    0.76
    RC
    0.75
     Hydro
    0.73
    BC
    0.72
    oreal
    0.72
    Activations Density 0.006%

    No Known Activations