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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 6-RES-JB
    6. 8521
    Prev
    Next
    INDEX
    Explanations

    films, TV shows, books, and other media works based on existing stories or sources

    oai_token-act-pair · gpt-3.5-turbo

    phrases that denote adaptations and films based on previous stories or works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĪĴ
    -0.90
    yip
    -0.83
    ciating
    -0.78
     spar
    -0.74
    hap
    -0.74
    dash
    -0.74
    resy
    -0.73
    alde
    -0.72
    atal
    -0.70
    ortex
    -0.70
    POSITIVE LOGITS
     starring
    0.95
     actresses
    0.89
     screenplay
    0.89
     acclaimed
    0.86
     actress
    0.83
     adaptation
    0.80
     premiered
    0.79
     anthology
    0.79
     remake
    0.76
     adapting
    0.76
    Activations Density 0.273%

    No Known Activations