© 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. 9-RES-JB
    11. 7600
    Prev
    Next
    INDEX
    Explanations

    text related to technical specifications or details such as model numbers and features

    oai_token-act-pair · gpt-3.5-turbo

    references to gaming or console specifications

    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
     guiName
    -0.88
    ":[{"
    -0.86
    etheless
    -0.83
    .<
    -0.82
    [/
    -0.80
    ADVERTISEMENT
    -0.73
     {*
    -0.72
     :=
    -0.72
    DragonMagazine
    -0.69
    âĶĢâĶĢâĶĢâĶĢ
    -0.68
    POSITIVE LOGITS
    )"
    1.55
    )
    1.52
    )."
    1.51
    ),
    1.45
    ):
    1.40
    ).
    1.39
    ?)
    1.39
    ),"
    1.38
    );
    1.38
    )/
    1.31
    Activations Density 0.293%

    No Known Activations