© 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. 10-RES-JB
    11. 10671
    Prev
    Next
    INDEX
    Explanations

    mentions of an action related to removing or kicking something or someone out

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Out" and its variations

    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
     arsen
    -0.87
    avorite
    -0.73
    interstitial
    -0.69
    OTT
    -0.65
    ione
    -0.63
    vre
    -0.63
    =-=-=-=-=-=-=-=-
    -0.61
     turnover
    -0.58
     misunder
    -0.57
     Metallic
    -0.56
    POSITIVE LOGITS
    doors
    1.20
    rage
    1.08
    dated
    1.07
    breaks
    1.03
    fitted
    1.01
    casts
    1.00
    landish
    0.99
    fits
    0.98
    come
    0.97
    raged
    0.97
    Activations Density 0.049%

    No Known Activations