© 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. 23827
    Prev
    Next
    INDEX
    Explanations

    names, likely related to individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to popular culture and significant events

    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
    ipeg
    -0.72
    itiveness
    -0.69
    ĵĺ
    -0.67
    Reviewed
    -0.65
    trial
    -0.63
    ?????-
    -0.62
    INTON
    -0.62
    kered
    -0.58
    achine
    -0.58
     ACTIONS
    -0.54
    POSITIVE LOGITS
    ibrary
    0.69
    ucc
    0.61
    aba
    0.58
    uala
    0.54
    umeric
    0.54
    pora
    0.53
    etus
    0.53
     Gaia
    0.52
     Giul
    0.52
     coli
    0.51
    Activations Density 1.400%

    No Known Activations