© 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. 10-RES-JB
    11. 23460
    Prev
    Next
    INDEX
    Explanations

    names of individuals and specific organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to popular culture, particularly television shows and social media phenomena

    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
     mileage
    -0.60
     marriages
    -0.57
     reads
    -0.54
     testimonies
    -0.52
     mobility
    -0.51
     adaptations
    -0.51
     refunds
    -0.51
     stretches
    -0.51
     journeys
    -0.50
     embodiments
    -0.50
    POSITIVE LOGITS
    $.
    1.12
    +.
    1.03
    _.
    0.98
    !.
    0.96
    .[
    0.94
    *.
    0.92
    >.
    0.85
     whereas
    0.83
    .
    0.82
    /,
    0.82
    Activations Density 0.787%

    No Known Activations