© 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. 8-RES-JB
    11. 7956
    Prev
    Next
    INDEX
    Explanations

    terms related to specific actions or objects, including terms related to athletics, personal grooming, and mechanical components

    oai_token-act-pair · gpt-3.5-turbo

    terms related to physical activities and elements of play

    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
    ãĥĥãĥī
    -0.77
    ãĤ¨ãĥ«
    -0.77
    Benz
    -0.70
    SEA
    -0.70
    ¿½
    -0.70
    æĢ
    -0.69
    ãĥ¯ãĥ³
    -0.69
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.68
    Newsletter
    -0.68
    VOL
    -0.68
    POSITIVE LOGITS
     extraord
    0.91
    hers
    0.75
    isters
    0.71
    rers
    0.70
    uction
    0.70
    chers
    0.69
    agers
    0.68
    er
    0.68
    ers
    0.68
    neau
    0.67
    Activations Density 0.748%

    No Known Activations