© 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. 15222
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a significant piece of information or instruction

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "Note that."

    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
    fu
    -0.68
    UME
    -0.66
     hur
    -0.62
    iever
    -0.62
     depended
    -0.62
    eal
    -0.61
    asio
    -0.61
    grounds
    -0.60
     Everest
    -0.59
    atown
    -0.59
    POSITIVE LOGITS
     wording
    0.77
     similarity
    0.72
     specificity
    0.69
     nuances
    0.66
     similarities
    0.66
    chy
    0.66
    xual
    0.65
     cumbers
    0.63
     detail
    0.62
     details
    0.61
    Activations Density 0.200%

    No Known Activations