© 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. 6-RES-JB
    11. 5124
    Prev
    Next
    INDEX
    Explanations

    sentences indicating certainty or incredulity

    oai_token-act-pair · gpt-3.5-turbo

    assertive statements or phrases that introduce certainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    insula
    -0.82
    psey
    -0.79
    anwhile
    -0.72
    arthed
    -0.72
    ocene
    -0.71
    lasses
    -0.70
    aution
    -0.70
    entary
    -0.68
    uese
    -0.67
    NING
    -0.66
    POSITIVE LOGITS
     someday
    0.76
    è¦
    0.74
     irritated
    0.71
     deserved
    0.70
     offended
    0.69
     suffice
    0.65
    apo
    0.65
     ric
    0.65
     forgiven
    0.64
    founded
    0.64
    Activations Density 0.023%

    No Known Activations