© 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. 7-RES-JB
    11. 17250
    Prev
    Next
    INDEX
    Explanations

    expressions of certainty or assurance

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating certainty or absoluteness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EStream
    -0.85
    isson
    -0.79
    zie
    -0.79
    åĤ
    -0.77
    beh
    -0.73
    worldly
    -0.72
    oga
    -0.72
    eways
    -0.71
    isure
    -0.70
    gee
    -0.69
    POSITIVE LOGITS
    heartedly
    0.71
     revolves
    0.70
     authentic
    0.67
     transparent
    0.65
     agree
    0.63
     automated
    0.63
     intentional
    0.63
     idiot
    0.63
     assured
    0.63
    rated
    0.62
    Activations Density 0.033%

    No Known Activations