© 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. 0-RES-JB
    11. 4050
    Prev
    Next
    INDEX
    Explanations

    adjectives related to shyness

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "shy."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    grounds
    -0.77
    papers
    -0.69
    adium
    -0.68
    usa
    -0.67
    quality
    -0.67
    altern
    -0.66
    blood
    -0.66
    contin
    -0.65
    endi
    -0.63
     Millennium
    -0.63
    POSITIVE LOGITS
     shy
    4.02
     timid
    1.53
     Shy
    1.33
     hesitate
    1.19
     coy
    1.19
     hesitant
    1.14
     afraid
    1.10
     embarrassed
    0.98
     ashamed
    0.97
     nervous
    0.96
    Activations Density 0.012%

    No Known Activations