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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 16393
    Prev
    Next
    INDEX
    Explanations

    words related to delicacy and care

    oai_token-act-pair · gpt-3.5-turbo

    adverbs that end with "ately."

    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
     Nap
    -0.65
     promise
    -0.58
    NRS
    -0.57
     ref
    -0.57
     Lag
    -0.56
     ban
    -0.55
     Link
    -0.54
     man
    -0.54
     promotion
    -0.54
     PubMed
    -0.54
    POSITIVE LOGITS
    ately
    4.59
    ate
    1.72
    ently
    1.56
    ates
    1.55
    acies
    1.52
    atically
    1.50
    atively
    1.47
    itely
    1.47
    ATE
    1.46
    ATES
    1.43
    Activations Density 0.009%

    No Known Activations