© 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. 11-RES-JB
    11. 3534
    Prev
    Next
    INDEX
    Explanations

    titles or professions related to academic fields or disciplines

    oai_token-act-pair · gpt-3.5-turbo

    references to academic roles and affiliations within higher education

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pload
    -0.67
     WARN
    -0.60
    oks
    -0.59
     Healer
    -0.59
     stret
    -0.58
     KILL
    -0.58
    Sov
    -0.57
    Score
    -0.57
    MSN
    -0.57
    imgur
    -0.56
    POSITIVE LOGITS
     emer
    0.97
     at
    0.90
     specializing
    0.89
     Emer
    0.88
     sciences
    0.86
     professor
    0.79
    chnology
    0.78
     Faculty
    0.78
     undergraduate
    0.78
     Languages
    0.78
    Activations Density 0.089%

    No Known Activations