© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 0-RES-JB
    11. 5259
    Prev
    Next
    INDEX
    Explanations

    proper names, particularly the name "Nash" followed by a number, and "Malkin" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Nash" and its different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     certificate
    -0.73
     serv
    -0.70
    course
    -0.70
     Certificate
    -0.69
     certific
    -0.67
    °
    -0.66
    EngineDebug
    -0.65
    º
    -0.65
     Cert
    -0.64
     INST
    -0.62
    POSITIVE LOGITS
     Nash
    4.24
     Malk
    1.40
     Nass
    1.16
     Ames
    1.12
     Kahn
    1.10
    Cass
    1.09
     Nashville
    1.04
     Sweeney
    1.03
     Somers
    1.03
     Naj
    1.03
    Activations Density 0.029%

    No Known Activations