© 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. 7-RES-JB
    11. 1891
    Prev
    Next
    INDEX
    Explanations

    names, most likely related to people

    oai_token-act-pair · gpt-3.5-turbo

    sequences of letters that commonly appear in names or proper nouns

    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
    ãĤ¼ãĤ¦ãĤ¹
    -0.70
    Spread
    -0.69
     loophole
    -0.62
    SPONSORED
    -0.61
     contradictions
    -0.59
     conveniently
    -0.58
     charism
    -0.58
     envy
    -0.57
     matched
    -0.56
     needle
    -0.55
    POSITIVE LOGITS
    kefeller
    0.95
    issance
    0.86
    restling
    0.79
    zl
    0.78
    ophone
    0.73
    backer
    0.72
    ighters
    0.71
    iger
    0.70
    earchers
    0.70
    undo
    0.69
    Activations Density 0.098%

    No Known Activations