© 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. 9-RES-JB
    11. 20755
    Prev
    Next
    INDEX
    Explanations

    words related to fitting, compatibility, or alignment

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to conformity or compatibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cember
    -0.68
    bies
    -0.66
    wcs
    -0.62
    affer
    -0.61
    externalActionCode
    -0.61
     descend
    -0.61
    icide
    -0.59
    escal
    -0.59
    icious
    -0.59
     salute
    -0.58
    POSITIVE LOGITS
     snug
    1.15
    gerald
    0.97
     into
    0.95
    ¶æ
    0.80
    nah
    0.77
    kat
    0.77
     squarely
    0.76
     comfortably
    0.74
     onto
    0.72
     neatly
    0.70
    Activations Density 0.045%

    No Known Activations