© 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. 2257
    Prev
    Next
    INDEX
    Explanations

    mentions of personal knowledge or beliefs

    oai_token-act-pair · gpt-3.5-turbo

    references to personal experiences and opinions

    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
     moderation
    -0.73
     smashing
    -0.69
     masc
    -0.68
     menstrual
    -0.67
     extravag
    -0.64
     festive
    -0.64
    interstitial
    -0.63
     gren
    -0.61
     scra
    -0.61
    Interstitial
    -0.60
    POSITIVE LOGITS
     know
    1.73
    know
    1.62
     KNOW
    1.58
    Know
    1.54
     Know
    1.53
     knows
    1.50
     knew
    1.49
    knowledge
    1.35
     knowing
    1.35
     knowledge
    1.24
    Activations Density 0.286%

    No Known Activations