© 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. 23526
    Prev
    Next
    INDEX
    Explanations

    information related to editing or editing areas

    oai_token-act-pair · gpt-3.5-turbo

    references to various forms of media, including books, movies, music, and television shows

    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
     sizing
    -0.76
     motorists
    -0.74
     barric
    -0.71
     clamp
    -0.71
     landowners
    -0.71
    stretched
    -0.71
    nel
    -0.70
     responders
    -0.70
     neighbours
    -0.70
     parking
    -0.70
    POSITIVE LOGITS
     sequels
    1.23
     genres
    1.23
     albums
    1.22
     genre
    1.19
     documentaries
    1.14
     classics
    1.11
    genre
    1.11
     anthology
    1.11
     novels
    1.10
     movies
    1.07
    Activations Density 0.921%

    No Known Activations