© 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. 16983
    Prev
    Next
    INDEX
    Explanations

    phrases indicating determination or intention

    oai_token-act-pair · gpt-3.5-turbo

    contractions and forms of "to be," especially in negative contexts

    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
    inav
    -0.80
    icle
    -0.66
    racuse
    -0.66
    udos
    -0.65
    odied
    -0.64
    icles
    -0.63
    ital
    -0.62
     pecul
    -0.61
    ciating
    -0.61
     resembles
    -0.60
    POSITIVE LOGITS
     gonna
    1.50
     willing
    1.41
     ready
    1.29
     going
    1.27
     prepared
    1.14
     sorry
    1.07
     obligated
    1.05
    ready
    1.01
     interested
    1.00
     afraid
    1.00
    Activations Density 0.248%

    No Known Activations