Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 2591
    Prev
    Next
    INDEX
    Explanations

    mentions of accountability or responsibility for actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of formal or informative content, particularly in the context of descriptions or accounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    Government
    -0.71
    .","
    -0.71
    ");
    -0.67
    itaire
    -0.64
    \"
    -0.64
    Manufact
    -0.63
    kefeller
    -0.62
    Increase
    -0.62
    `.
    -0.61
    government
    -0.61
    POSITIVE LOGITS
     Dunham
    0.80
     gigg
    0.79
     chuckled
    0.78
     reply
    0.77
     amused
    0.77
    yrics
    0.77
     laughs
    0.77
     replies
    0.77
     Gawker
    0.76
     Whedon
    0.75
    Activations Density 1.205%

    No Known Activations