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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4-RES-JB
    11. 10122
    Prev
    Next
    INDEX
    Explanations

    the name "Conway" within a document

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Conway."

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

    No Comments

    Negative Logits
    axy
    -0.69
     debtor
    -0.67
    Magikarp
    -0.67
     humanities
    -0.64
     delinquent
    -0.62
    gio
    -0.61
    hig
    -0.61
     creditor
    -0.61
     Antar
    -0.60
    cgi
    -0.59
    POSITIVE LOGITS
     Conway
    1.16
    quist
    0.86
    anooga
    0.80
    naissance
    0.80
     McConnell
    0.77
    nect
    0.77
    swer
    0.76
    gru
    0.73
    structed
    0.73
     Osw
    0.72
    Activations Density 0.010%

    No Known Activations