© 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. 8-RES-JB
    11. 20259
    Prev
    Next
    INDEX
    Explanations

    numerical references and legal or formal terms like names, numbers, and order titles

    oai_token-act-pair · gpt-3.5-turbo

    references to legal or judicial identities and processes

    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
     congratulated
    -0.73
     modem
    -0.72
    vernment
    -0.68
     keyboard
    -0.65
    tarian
    -0.65
     unaff
    -0.64
     lifestyle
    -0.63
     mechanically
    -0.63
     education
    -0.63
     treadmill
    -0.63
    POSITIVE LOGITS
    ĸļ
    1.01
    XXX
    1.01
     XXX
    1.00
     Nos
    1.00
     XIII
    0.99
     XIV
    0.95
     supra
    0.94
     XVI
    0.90
     01
    0.88
     #
    0.85
    Activations Density 0.704%

    No Known Activations