© 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 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. 11-RES-JB
    11. 14933
    Prev
    Next
    INDEX
    Explanations

    names or mentions of individuals

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter "H" in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Scully
    -0.83
    enhagen
    -0.71
     Cullen
    -0.67
     Kers
    -0.67
     Standing
    -0.66
     Lerner
    -0.66
     Ballard
    -0.66
     Clause
    -0.66
     Bunny
    -0.64
     Reeves
    -0.63
    POSITIVE LOGITS
    adi
    1.25
    aji
    1.02
    eday
    0.99
    ani
    0.97
    allel
    0.95
    abis
    0.94
    afi
    0.94
    uda
    0.94
    edi
    0.94
    iday
    0.94
    Activations Density 0.033%

    No Known Activations