© 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. 11274
    Prev
    Next
    INDEX
    Explanations

    references to open-ended concepts or discussions

    oai_token-act-pair · gpt-3.5-turbo

    references to openness in discussions or proposals

    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
    CTV
    -0.70
    iage
    -0.66
    verages
    -0.65
    doms
    -0.62
    rior
    -0.61
    dos
    -0.61
     Kamp
    -0.61
    yz
    -0.60
     Monstrous
    -0.60
    ibur
    -0.60
    POSITIVE LOGITS
     minded
    0.96
     source
    0.83
    ource
    0.83
    street
    0.79
     eyed
    0.78
    ended
    0.78
     borders
    0.77
     sourced
    0.76
     invitation
    0.75
     doors
    0.75
    Activations Density 0.051%

    No Known Activations