© 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. 10-RES-JB
    11. 20311
    Prev
    Next
    INDEX
    Explanations

    phrases indicating caution or warnings

    oai_token-act-pair · gpt-3.5-turbo

    mentions of being careful or cautious

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    upon
    -0.80
    IRE
    -0.66
    heid
    -0.64
    MH
    -0.64
    flat
    -0.64
    ono
    -0.62
    hung
    -0.61
    obo
    -0.60
    soon
    -0.60
    olon
    -0.60
    POSITIVE LOGITS
     lest
    1.12
     calibr
    0.80
     selecting
    0.69
     when
    0.69
    rored
    0.69
     interpreting
    0.69
    ^^
    0.67
     regarding
    0.66
    ogical
    0.66
     stewards
    0.65
    Activations Density 0.078%

    No Known Activations