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

    Neuronpedia

    Jacobian LensNEW
    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. 4-RES-JB
    11. 6985
    Prev
    Next
    INDEX
    Explanations

    mentions of the online art community platform DeviantArt

    oai_token-act-pair · gpt-3.5-turbo

    repeated patterns of the term "iant" in various contexts

    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
    agan
    -0.80
    OUT
    -0.77
    assic
    -0.74
    MER
    -0.74
    cffffcc
    -0.73
    earchers
    -0.73
    uberty
    -0.72
    mers
    -0.72
    horn
    -0.72
    uggage
    -0.72
    POSITIVE LOGITS
    riad
    0.87
    enance
    0.78
    yne
    0.76
    eca
    0.72
    naire
    0.72
    ãĥ¼ãĥĨãĤ£
    0.70
    ept
    0.70
     IMAGES
    0.70
    ãĥĨ
    0.69
    ieth
    0.69
    Activations Density 0.018%

    No Known Activations