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. 4-RES-JB
    6. 286
    Prev
    Next
    INDEX
    Explanations

    cryptocurrency related terms, specifically those related to the cryptocurrency "Bit."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the cryptocurrency "Bitcoin" and its related terms

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

    No Comments

    Negative Logits
    ammad
    -0.85
    ammed
    -0.78
    inson
    -0.72
    ãĥ¯
    -0.67
    swick
    -0.67
    éĸ
    -0.66
    PsyNetMessage
    -0.66
    INE
    -0.66
    ities
    -0.65
     Siber
    -0.65
    POSITIVE LOGITS
    terness
    1.29
    coins
    1.02
    Shares
    0.96
    umen
    0.95
    buck
    0.92
    Torrent
    0.91
    umin
    0.85
    fine
    0.83
    unia
    0.82
    Coin
    0.82
    Activations Density 0.010%

    No Known Activations