© 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. 23117
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to historical or cultural references

    oai_token-act-pair · gpt-3.5-turbo

    specific historical names and locations

    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
    ĸļ
    -0.68
     centrif
    -0.66
     Ort
    -0.65
     numbering
    -0.65
    papers
    -0.61
    nesota
    -0.60
     Expend
    -0.59
     USAF
    -0.57
     Vert
    -0.57
     Mold
    -0.56
    POSITIVE LOGITS
    apest
    0.82
    illion
    0.81
    Ãł
    0.74
    illet
    0.73
    é¾įå
    0.72
    oor
    0.71
    omew
    0.71
    erenn
    0.71
    oola
    0.70
    ava
    0.70
    Activations Density 0.209%

    No Known Activations