© 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. 6985
    Prev
    Next
    INDEX
    Explanations

    professional statements or press releases

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases involving "in a" and "a" within various statements

    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
    Exper
    -0.72
    models
    -0.66
    rity
    -0.64
     experimented
    -0.64
    killers
    -0.64
    Mods
    -0.63
    fights
    -0.63
     Avenger
    -0.62
    âī
    -0.62
    enemy
    -0.62
    POSITIVE LOGITS
     statement
    1.55
     memo
    1.10
     memorandum
    1.06
     tweet
    1.06
     letter
    1.03
     press
    1.03
     telephone
    1.03
     blog
    1.02
     written
    1.01
    statement
    0.99
    Activations Density 0.066%

    No Known Activations