© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 10250
    Prev
    Next
    INDEX
    Explanations

    words related to reactions or responses to stimuli

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "respond" and its variations in the context of reactions or replies

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    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
    Negative Logits
    dar
    -0.73
    corn
    -0.68
    thing
    -0.65
    colo
    -0.62
    fre
    -0.62
    borne
    -0.61
     Dracula
    -0.60
    =-=-=-=-=-=-=-=-
    -0.58
    fi
    -0.58
    fusc
    -0.58
    POSITIVE LOGITS
     favorably
    1.20
     positively
    1.14
    ivated
    1.03
     angrily
    1.02
     thereto
    1.01
     negatively
    0.96
     harshly
    0.94
     enthusiastically
    0.91
     promptly
    0.90
     appropriately
    0.90
    Activations Density 0.050%

    No Known Activations