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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 11907
    Prev
    Next
    INDEX
    Explanations

    contradictions or opposing statements

    oai_token-act-pair · gpt-3.5-turbo

    negative statements regarding health and medical outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sidx
    -0.81
    abouts
    -0.72
    GBT
    -0.71
    JM
    -0.70
    CF
    -0.69
    risome
    -0.67
    Links
    -0.67
    Rev
    -0.66
     Appears
    -0.66
    20439
    -0.66
    POSITIVE LOGITS
     infall
    1.16
     necessarily
    1.04
     overnight
    1.03
     perfect
    0.97
     always
    0.97
     substitute
    0.96
     synonymous
    0.95
     magically
    0.93
     cure
    0.92
     ALWAYS
    0.89
    Activations Density 0.267%

    No Known Activations