© 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. 8-RES-JB
    11. 19383
    Prev
    Next
    INDEX
    Explanations

    names of universities and colleges

    oai_token-act-pair · gpt-3.5-turbo

    references to various universities and colleges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    usting
    -0.83
    ttle
    -0.74
    eto
    -0.69
    ._
    -0.68
    erity
    -0.66
    retty
    -0.64
    vous
    -0.63
    .—
    -0.62
    ?:
    -0.61
    ura
    -0.60
    POSITIVE LOGITS
     lith
    0.66
     differential
    0.63
     FI
    0.63
     delinqu
    0.61
     cellul
    0.59
     Cyborg
    0.59
     Neph
    0.58
     hydra
    0.58
     Lith
    0.58
    phan
    0.57
    Activations Density 0.271%

    No Known Activations