© 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. 4-RES-JB
    11. 6653
    Prev
    Next
    INDEX
    Explanations

    handwritten or typed notes in text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "note" in various contexts

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

    No Comments

    Negative Logits
     persecut
    -0.72
    ãĥĩ
    -0.69
     displ
    -0.66
     Predators
    -0.65
    ibaba
    -0.64
    heed
    -0.63
    emouth
    -0.63
     waged
    -0.62
     plaintiffs
    -0.60
     indignation
    -0.60
    POSITIVE LOGITS
    notes
    1.08
    BOOK
    1.01
    books
    0.95
    book
    0.93
    Pad
    0.87
    pee
    0.83
    ably
    0.79
    ariat
    0.77
    atur
    0.76
     Notes
    0.75
    Activations Density 0.026%

    No Known Activations