© 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 EvalsExportsinterp-engineNEWAPI 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. 10-RES-JB
    11. 18966
    Prev
    Next
    INDEX
    Explanations

    mentions of specific names

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of certain 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 @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nown
    -0.94
    undo
    -0.86
    orius
    -0.86
    imov
    -0.85
    alach
    -0.84
    arak
    -0.84
    pmwiki
    -0.84
    umatic
    -0.83
    perm
    -0.81
    llular
    -0.81
    POSITIVE LOGITS
     Jenner
    1.26
     Kardashian
    1.05
     Reynolds
    1.03
     Dunn
    1.01
     Lynn
    1.00
     Michaels
    1.00
     McKenna
    0.99
     Duff
    0.99
     Collins
    0.97
     McCann
    0.97
    Activations Density 0.101%

    No Known Activations