© 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. 11473
    Prev
    Next
    INDEX
    Explanations

    issues or topics of discussion

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various pressing issues

    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
    ramid
    -0.84
    urses
    -0.81
    ãĥ³ãĤ¸
    -0.80
    onz
    -0.74
    glas
    -0.71
    son
    -0.71
    rams
    -0.71
    ellow
    -0.70
    mingham
    -0.70
    SON
    -0.69
    POSITIVE LOGITS
     plag
    1.00
     confronting
    1.00
     arising
    0.97
     affecting
    0.95
     raised
    0.95
     flared
    0.95
     facing
    0.91
     arise
    0.90
     relating
    0.90
     resolved
    0.89
    Activations Density 0.070%

    No Known Activations