© 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. 6447
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to accusations or blame

    oai_token-act-pair · gpt-3.5-turbo

    mentions of individuals or entities associated with accusations

    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
    æĸ¹
    -0.65
     attest
    -0.63
    nov
    -0.62
    udeb
    -0.56
    areth
    -0.56
    regulated
    -0.56
     UCHIJ
    -0.55
     invests
    -0.55
     warr
    -0.54
    thus
    -0.54
    POSITIVE LOGITS
     of
    0.88
     unfairly
    0.85
     thereof
    0.82
     falsely
    0.78
     wrongly
    0.74
     unjust
    0.69
    ims
    0.68
     misleading
    0.68
    of
    0.66
     inaction
    0.66
    Activations Density 0.074%

    No Known Activations