© 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. 10-RES-JB
    11. 16033
    Prev
    Next
    INDEX
    Explanations

    words related to confidence and assurance

    oai_token-act-pair · gpt-3.5-turbo

    expressions of approval or disapproval in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Controls
    -0.74
    pleted
    -0.73
    Thousands
    -0.73
     Scores
    -0.73
     Rooms
    -0.73
    orest
    -0.71
    Prev
    -0.71
    uilding
    -0.70
     Located
    -0.69
    oother
    -0.69
    POSITIVE LOGITS
     understatement
    1.44
     rhetorical
    1.41
     irony
    1.40
     sarc
    1.24
     sarcastic
    1.23
     cynicism
    1.22
     cliché
    1.21
     euphem
    1.19
     phr
    1.17
     paraph
    1.14
    Activations Density 0.661%

    No Known Activations