© 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. 23483
    Prev
    Next
    INDEX
    Explanations

    references to specific people and organizations, particularly related to reports, investments, and hiring

    oai_token-act-pair · gpt-3.5-turbo

    mentions of interviews or related interactions

    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
     util
    -0.76
    à©
    -0.74
    ãĥİ
    -0.73
    uminium
    -0.72
     exting
    -0.71
    beit
    -0.70
     formations
    -0.69
    Compat
    -0.69
    ÙIJ
    -0.69
    fal
    -0.69
    POSITIVE LOGITS
     Gawker
    1.13
     Huffington
    1.02
     FOIA
    1.01
     AOL
    0.95
     Yelp
    0.95
     Pulitzer
    0.94
     NYU
    0.93
     BuzzFeed
    0.93
     Gamergate
    0.93
     Fiorina
    0.93
    Activations Density 1.393%

    No Known Activations