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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 9980
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of "surprise" or "surmising"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "sur" or its variations, likely signaling discussions related to surrender or submission

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arians
    -0.73
     Rosenstein
    -0.60
     affili
    -0.60
     orbits
    -0.60
    arian
    -0.59
    itsch
    -0.59
     Feder
    -0.58
     attorneys
    -0.58
     upright
    -0.58
     Unch
    -0.57
    POSITIVE LOGITS
    mounted
    1.29
    charge
    1.20
    mount
    1.17
    geon
    1.09
    render
    1.07
    rounded
    1.05
    tro
    1.03
    fer
    1.02
    prise
    1.02
    rendered
    1.02
    Activations Density 0.010%

    No Known Activations