© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 10285
    Prev
    Next
    INDEX
    Explanations

    websites or sources for further information or updates

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate a request for additional information or details

    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
    conn
    -0.82
    sonian
    -0.80
    igr
    -0.75
    ÃŃs
    -0.75
    iltr
    -0.73
    rn
    -0.72
    ãĥĺ
    -0.72
    `
    -0.70
    asse
    -0.70
    pour
    -0.69
    POSITIVE LOGITS
     details
    1.31
     directions
    1.06
     answers
    1.04
     instructions
    1.00
     specifics
    1.00
     info
    1.00
     clarification
    0.98
     detailed
    0.98
     updates
    0.97
     more
    0.94
    Activations Density 0.104%

    No Known Activations