© 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. 6-RES-JB
    11. 23734
    Prev
    Next
    INDEX
    Explanations

    protein interactions in a molecular context

    oai_token-act-pair · gpt-3.5-turbo

    instances of repetitive phrases or structures in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     retali
    -0.85
     oath
    -0.75
     battleground
    -0.73
     veto
    -0.72
     allies
    -0.70
     overth
    -0.70
     Kremlin
    -0.70
     appe
    -0.69
     undercut
    -0.68
     compromising
    -0.68
    POSITIVE LOGITS
    Young
    0.97
    Owner
    0.95
    Courtesy
    0.93
    Loc
    0.93
    TY
    0.90
    Artist
    0.88
    Enlarge
    0.87
    Hidden
    0.86
    His
    0.86
    Interview
    0.84
    Activations Density 0.604%

    No Known Activations