© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 0-RES-JB
    11. 8335
    Prev
    Next
    INDEX
    Explanations

    references to actors

    oai_token-act-pair · gpt-3.5-turbo

    references to actors and actresses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aults
    -0.75
    yrs
    -0.70
    tops
    -0.68
    wn
    -0.64
    hops
    -0.63
    ills
    -0.63
    RESULTS
    -0.63
    compl
    -0.62
    ür
    -0.62
    cling
    -0.62
    POSITIVE LOGITS
     actor
    3.84
     actress
    2.83
     Actor
    2.64
     actors
    2.58
    Actor
    2.49
     Actress
    1.94
     filmmaker
    1.81
     comedian
    1.78
    actor
    1.73
     singer
    1.69
    Activations Density 0.020%

    No Known Activations