© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 22665
    Prev
    Next
    INDEX
    Explanations

    references to reviews or assessments of different subjects

    oai_token-act-pair · gpt-3.5-turbo

    references to evaluations or assessments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Notable
    -0.71
    enegger
    -0.67
    Favorite
    -0.63
    liners
    -0.62
    Love
    -0.60
    Spread
    -0.59
    absolute
    -0.59
    Temperature
    -0.58
     Infinite
    -0.57
     ç¥ŀ
    -0.57
    POSITIVE LOGITS
     process
    1.29
     undertaken
    1.06
     committee
    1.04
     conducted
    1.02
     panel
    1.01
     commissioned
    0.99
     board
    0.99
     Panel
    0.99
     procedure
    0.97
     audit
    0.97
    Activations Density 0.108%

    No Known Activations