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

    Neuronpedia

    APICircuit 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. 8-RES-JB
    6. 16307
    Prev
    Next
    INDEX
    Explanations

    keyword matches for the acronym "BC" with different suffixes like "Business" and "Hydro"

    oai_token-act-pair · gpt-3.5-turbo

    references to "BC" as it relates to specific contexts or organizations

    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
    mble
    -0.93
    ktop
    -0.77
    istration
    -0.71
    ners
    -0.70
    stice
    -0.68
    zzle
    -0.68
    boat
    -0.67
    geant
    -0.65
    cha
    -0.65
    boats
    -0.64
    POSITIVE LOGITS
    BG
    0.87
    osta
    0.83
    orne
    0.83
    ORN
    0.83
    IJ
    0.83
    oreal
    0.81
    ASE
    0.81
    rypt
    0.80
    razy
    0.80
    ode
    0.79
    Activations Density 0.021%

    No Known Activations