© 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. 8-RES-JB
    11. 20041
    Prev
    Next
    INDEX
    Explanations

    the word "can" followed by statements raising questions or discussing possibilities

    oai_token-act-pair · gpt-3.5-turbo

    questions that start with "How can."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RAFT
    -0.77
    displayText
    -0.66
    hig
    -0.61
    hog
    -0.60
    Russ
    -0.60
     ported
    -0.59
    edge
    -0.58
    yssey
    -0.58
    vez
    -0.58
     threaded
    -0.57
    POSITIVE LOGITS
    berra
    1.15
    't
    1.11
    adian
    0.79
     anyone
    0.75
    ary
    0.73
    gow
    0.73
     anybody
    0.72
    ?]
    0.72
    aries
    0.71
    ADA
    0.71
    Activations Density 0.045%

    No Known Activations