© 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. 23122
    Prev
    Next
    INDEX
    Explanations

    words related to the tongue or oral activities

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the word "tongue" and related terms

    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
    ded
    -0.87
    rals
    -0.77
    illon
    -0.75
    schild
    -0.74
    ding
    -0.74
    ramid
    -0.71
    iary
    -0.70
    icipated
    -0.70
    EMS
    -0.68
    kus
    -0.66
    POSITIVE LOGITS
     tongue
    0.93
     tongues
    0.84
     fry
    0.78
    warm
    0.77
    ice
    0.76
    ingen
    0.75
    mith
    0.75
     slur
    0.72
     cleans
    0.71
     wrinkles
    0.70
    Activations Density 0.035%

    No Known Activations