© 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. 4092
    Prev
    Next
    INDEX
    Explanations

    names of scandals or highly controversial events

    oai_token-act-pair · gpt-3.5-turbo

    references to high-profile legal cases or controversies

    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
    essential
    -0.74
    ivably
    -0.70
    ighty
    -0.70
    uitive
    -0.69
    Cath
    -0.69
    anguages
    -0.67
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.66
    ãĥĨãĤ£
    -0.65
    ellen
    -0.64
    tml
    -0.64
    POSITIVE LOGITS
     scandal
    1.83
     fiasco
    1.74
     debacle
    1.71
     scandals
    1.56
     controversy
    1.52
     affair
    1.52
     incident
    1.49
     allegations
    1.45
     saga
    1.44
     allegation
    1.38
    Activations Density 0.571%

    No Known Activations