© 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. 10-RES-JB
    11. 4912
    Prev
    Next
    INDEX
    Explanations

    companies and proper nouns in a list format

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    igent
    -0.68
    pection
    -0.68
     overflow
    -0.67
    FORMATION
    -0.67
     exting
    -0.66
    afety
    -0.65
    hemer
    -0.64
     stalls
    -0.64
     scrimmage
    -0.63
    essa
    -0.62
    POSITIVE LOGITS
     Volkswagen
    1.06
     Tesla
    1.03
     Porsche
    1.02
     Flavoring
    1.01
     Ferrari
    0.98
     Exxon
    0.97
     Samsung
    0.97
    Samsung
    0.96
     BlackBerry
    0.94
     Starbucks
    0.94
    Activations Density 0.593%

    No Known Activations