© 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. 9-RES-JB
    11. 11245
    Prev
    Next
    INDEX
    Explanations

    statements providing explanations or descriptions of concepts or observations

    oai_token-act-pair · gpt-3.5-turbo

    scholarly assertions and citations

    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
    SHARE
    -0.69
    wives
    -0.64
     condol
    -0.64
    Cele
    -0.61
    fired
    -0.59
    ranged
    -0.58
    luck
    -0.58
     clicked
    -0.58
    naissance
    -0.58
    thumbnails
    -0.57
    POSITIVE LOGITS
     convinc
    0.94
     extensively
    0.85
     empir
    0.82
     rhet
    0.81
     quotes
    0.81
     "âĢ¦
    0.81
     anecdotes
    0.78
     explicitly
    0.77
     quoting
    0.76
     "...
    0.75
    Activations Density 0.303%

    No Known Activations