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

    Neuronpedia

    Jacobian LensNEW
    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. 9-RES-JB
    11. 16031
    Prev
    Next
    INDEX
    Explanations

    rhetorical questions or phrases that imply agreement or affirmation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    conversational phrases that seek agreement or validation

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cosponsors
    -0.64
    ounters
    -0.60
     Foods
    -0.60
    ounter
    -0.59
    ifax
    -0.58
    ilogy
    -0.57
    hetti
    -0.56
    esa
    -0.56
    quished
    -0.55
    irting
    -0.55
    POSITIVE LOGITS
    kay
    0.95
    cause
    0.91
     eh
    0.81
     ya
    0.78
     traveller
    0.76
     sir
    0.76
     huh
    0.73
     mortal
    0.73
    ?).
    0.67
    kie
    0.66
    Activations Density 0.203%

    No Known Activations