© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 1449
    Prev
    Next
    INDEX
    Explanations

    content related to technical information and warnings

    oai_token-act-pair · gpt-3.5-turbo

    content related to timelines and documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    naire
    -0.77
    ariat
    -0.77
    etts
    -0.74
    naires
    -0.72
    forth
    -0.71
    tein
    -0.69
    hop
    -0.68
    ctors
    -0.66
    ivas
    -0.66
    iewicz
    -0.66
    POSITIVE LOGITS
    Movie
    0.86
     Manga
    0.71
     Seller
    0.68
    Title
    0.68
    iframe
    0.67
    Ble
    0.64
     DISTRICT
    0.63
    Runtime
    0.63
    Drug
    0.62
    cloneembedreportprint
    0.62
    Activations Density 0.616%

    No Known Activations