© 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. 21475
    Prev
    Next
    INDEX
    Explanations

    references to authority figures or institutions making decisions

    oai_token-act-pair · gpt-3.5-turbo

    content related to judicial decisions and legal proceedings

    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
    Beaut
    -0.74
    Life
    -0.68
    Growing
    -0.67
     Explosion
    -0.65
     Whats
    -0.65
     Beauty
    -0.63
    Dad
    -0.62
     Paste
    -0.62
    Memory
    -0.61
     highs
    -0.61
    POSITIVE LOGITS
     subpoena
    1.44
     veto
    1.28
     overr
    1.22
     unilaterally
    1.21
     subpoen
    1.20
     filib
    1.16
     enforce
    1.11
     legisl
    1.11
     filibuster
    1.10
     acquies
    1.09
    Activations Density 0.446%

    No Known Activations