© 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. 10165
    Prev
    Next
    INDEX
    Explanations

    references to story plots or plans of action

    oai_token-act-pair · gpt-3.5-turbo

    references to plots or schemes in narratives

    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
    IDA
    -0.71
    agles
    -0.69
    angelo
    -0.69
    Downloadha
    -0.66
    ertodd
    -0.64
    ILA
    -0.62
     Jazz
    -0.62
    Scot
    -0.62
     Gi
    -0.62
     Lak
    -0.61
    POSITIVE LOGITS
    ters
    0.88
     plot
    0.86
     Plot
    0.84
     twists
    0.83
    lines
    0.82
    line
    0.79
     plotting
    0.77
    ories
    0.77
    cases
    0.76
    tle
    0.76
    Activations Density 0.017%

    No Known Activations