© 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. 10-RES-JB
    11. 14172
    Prev
    Next
    INDEX
    Explanations

    praising or criticizing adjectives for describing individuals

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize positive attributes and characteristics

    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
    Events
    -0.76
    events
    -0.75
    eworks
    -0.74
    Attach
    -0.73
    Items
    -0.73
    articles
    -0.72
    views
    -0.72
    ARB
    -0.71
    IRC
    -0.70
    uden
    -0.70
    POSITIVE LOGITS
     liar
    1.28
     hypocr
    1.26
     believer
    1.19
     coward
    1.13
     genius
    1.11
     terrific
    1.09
     brilliant
    1.08
     talented
    1.08
     bigot
    1.07
     fearless
    1.07
    Activations Density 0.138%

    No Known Activations