© 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. 4-RES-JB
    11. 7502
    Prev
    Next
    INDEX
    Explanations

    attributes related to size or quantity

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "enough" 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
     Guth
    -0.84
    eston
    -0.69
    bull
    -0.68
    folk
    -0.66
    eva
    -0.65
    eworthy
    -0.61
     coron
    -0.61
    anian
    -0.61
    analysis
    -0.60
    misc
    -0.60
    POSITIVE LOGITS
    -+-+
    0.64
     ILCS
    0.64
    osponsors
    0.62
    ................
    0.61
    xff
    0.61
    hots
    0.60
    Label
    0.59
     Puzzles
    0.59
     dstg
    0.59
    HUD
    0.59
    Activations Density 0.021%

    No Known Activations