© 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. 7-RES-JB
    11. 12406
    Prev
    Next
    INDEX
    Explanations

    words related to reactions and responses

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "reaction" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hold
    -0.74
     Sinai
    -0.74
    holder
    -0.73
    iciency
    -0.71
    locked
    -0.66
    fficiency
    -0.62
    enture
    -0.61
    cipled
    -0.60
    red
    -0.60
    soDeliveryDate
    -0.59
    POSITIVE LOGITS
    ivated
    1.25
     reactions
    1.17
    aries
    1.14
     reaction
    1.13
    ivating
    1.10
    ivation
    1.08
     Reaction
    1.04
     negatively
    0.87
    iv
    0.86
     thereto
    0.82
    Activations Density 0.033%

    No Known Activations