© 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. 11-RES-JB
    11. 18600
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences containing the word "response."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "in response to."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chin
    -0.66
    hold
    -0.66
    flo
    -0.63
    stall
    -0.59
    oiler
    -0.59
    necess
    -0.57
    locked
    -0.56
    milo
    -0.55
    ezvous
    -0.55
    redo
    -0.55
    POSITIVE LOGITS
     thereto
    1.22
     to
    0.97
    PsyNetMessage
    0.71
     TO
    0.67
     To
    0.63
    to
    0.60
    ļéĨĴ
    0.60
    awn
    0.59
     remarks
    0.55
    externalActionCode
    0.55
    Activations Density 0.035%

    No Known Activations