© 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. 11-RES-JB
    11. 4138
    Prev
    Next
    INDEX
    Explanations

    references to specific countries, particularly Canada and Australia

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Canadian and Australian entities or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sylv
    -0.78
    idious
    -0.77
    bably
    -0.73
    essler
    -0.72
    pots
    -0.71
    lets
    -0.70
    _>
    -0.70
    lov
    -0.69
    eus
    -0.68
    atz
    -0.67
    POSITIVE LOGITS
     Broadcasting
    1.40
     Securities
    1.10
     Institutes
    1.09
     Forces
    1.08
     Federation
    1.06
     Association
    1.05
     Journalists
    1.05
     Standards
    1.03
     Government
    1.01
     Psychological
    1.01
    Activations Density 0.086%

    No Known Activations