© 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. 8-RES-JB
    11. 6801
    Prev
    Next
    INDEX
    Explanations

    settings or locations within a visual storytelling context

    oai_token-act-pair · gpt-3.5-turbo

    references to specific scenes in films or movies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bred
    -0.85
    ickson
    -0.69
    jri
    -0.68
    ija
    -0.68
    resy
    -0.67
    quartered
    -0.67
    ovo
    -0.66
    ãĤ¦ãĤ¹
    -0.65
    ifestyle
    -0.65
    brand
    -0.64
    POSITIVE LOGITS
     depicting
    0.98
    Dialogue
    0.95
     featuring
    0.94
     filmed
    0.94
     aired
    0.94
     airing
    0.91
     mont
    0.88
    scene
    0.88
     scenes
    0.85
     narration
    0.85
    Activations Density 0.281%

    No Known Activations