© 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. 3-RES-JB
    11. 1573
    Prev
    Next
    INDEX
    Explanations

    statements emphasizing absolute certainty or lack of doubt

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize certainty or totality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ritz
    -0.80
    ku
    -0.77
    por
    -0.76
    lines
    -0.75
    bern
    -0.74
    eds
    -0.74
    iv
    -0.73
    yi
    -0.73
    eg
    -0.73
    ahime
    -0.72
    POSITIVE LOGITS
    soever
    1.30
    THING
    1.13
     whatsoever
    1.10
     else
    1.05
     remotely
    0.90
    wcsstore
    0.87
     except
    0.87
     imaginable
    0.86
     conceivable
    0.85
    lihood
    0.83
    Activations Density 0.007%

    No Known Activations