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. 1-RES-JB
    6. 11763
    Prev
    Next
    INDEX
    Explanations

    references to historical figures and famous characters from various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to historical figures, particularly philosophers and notable personalities

    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
    WN
    -0.86
    CLA
    -0.77
    LU
    -0.75
    RAM
    -0.73
    WF
    -0.73
    VG
    -0.73
    WI
    -0.70
    leigh
    -0.70
    CI
    -0.69
    ve
    -0.68
    POSITIVE LOGITS
     Cthulhu
    0.96
     Reincarn
    0.82
    ocrates
    0.82
     Lovecraft
    0.81
    jriwal
    0.78
     Napoleon
    0.75
     Tsukuyomi
    0.75
     fascinated
    0.71
     Horus
    0.70
    emort
    0.69
    Activations Density 0.023%

    No Known Activations