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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 20178
    Prev
    Next
    INDEX
    Explanations

    responses or reactions to stimuli or requests

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "respond."

    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
     rumours
    -0.70
     Knot
    -0.68
     Dynasty
    -0.66
     Guinness
    -0.64
     rumors
    -0.64
    held
    -0.61
    gin
    -0.59
    bare
    -0.59
     dynasty
    -0.58
     trophies
    -0.58
    POSITIVE LOGITS
     respond
    3.49
     responds
    2.43
     responding
    2.27
     responded
    2.21
     response
    2.14
     reply
    2.09
    respond
    2.03
     Respond
    2.01
    response
    1.95
     responses
    1.80
    Activations Density 0.016%

    No Known Activations