© 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. 9-RES-JB
    11. 5264
    Prev
    Next
    INDEX
    Explanations

    proper names related to people

    oai_token-act-pair · gpt-3.5-turbo

    references to specific named individuals and notable figures, particularly those associated with the arts and entertainment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    grave
    -0.88
    maid
    -0.85
    fulness
    -0.85
    creen
    -0.85
    ships
    -0.82
    igans
    -0.81
    cil
    -0.80
    acle
    -0.80
    oÄŁ
    -0.79
    fully
    -0.79
    POSITIVE LOGITS
     Romero
    0.99
     Wilde
    0.95
     Pist
    0.88
     Mayer
    0.85
     Flores
    0.82
     Lup
    0.82
     Aires
    0.82
     Zam
    0.81
     Morales
    0.80
     Diaz
    0.79
    Activations Density 0.121%

    No Known Activations