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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 4046
    Prev
    Next
    INDEX
    Explanations

    descriptions or evaluations related to technology features

    oai_token-act-pair · gpt-3.5-turbo

    descriptions related to quality and performance

    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
    reprene
    -0.75
    href
    -0.73
    agine
    -0.73
    [_
    -0.68
     Pension
    -0.68
    ARGET
    -0.67
    olitan
    -0.67
    ceivable
    -0.67
     jointly
    -0.66
    erenn
    -0.66
    POSITIVE LOGITS
    Overall
    1.08
     gri
    1.01
     Overall
    0.99
     brightness
    0.99
     noticeable
    0.98
     matte
    0.97
     noticeably
    0.97
     responsiveness
    0.94
     erg
    0.90
     downside
    0.89
    Activations Density 0.533%

    No Known Activations