© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10-RES-JB
    11. 3145
    Prev
    Next
    INDEX
    Explanations

    references to large quantities of money or value

    oai_token-act-pair · gpt-3.5-turbo

    references to large quantities of people or financial amounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iban
    -0.62
     Redemption
    -0.62
    imen
    -0.56
    ãĥ¤
    -0.55
     compar
    -0.53
     cannabin
    -0.53
     limitations
    -0.52
    amina
    -0.52
     moderator
    -0.52
     confir
    -0.52
    POSITIVE LOGITS
    aires
    1.05
    aire
    0.99
     upon
    0.98
    dollar
    0.93
     of
    0.92
    undo
    0.87
     dollars
    0.82
    ously
    0.76
    naire
    0.74
     dollar
    0.74
    Activations Density 0.042%

    No Known Activations