© 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. 6-RES-JB
    11. 7407
    Prev
    Next
    INDEX
    Explanations

    words related to emphasis and certainty

    oai_token-act-pair · gpt-3.5-turbo

    the word "definitely" and its variations, indicating certainty or emphasis

    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
    Reviewer
    -0.82
    roups
    -0.81
    acity
    -0.80
    sembly
    -0.80
    bestos
    -0.75
    mits
    -0.73
    glers
    -0.73
    lings
    -0.72
    gencies
    -0.70
    ufact
    -0.69
    POSITIVE LOGITS
     qualifies
    0.68
     Vader
    0.68
     disqual
    0.67
     underest
    0.67
     deline
    0.66
     impacted
    0.65
     recommend
    0.65
     differentiated
    0.63
     identifiable
    0.63
     exagger
    0.62
    Activations Density 0.023%

    No Known Activations