© 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. 2828
    Prev
    Next
    INDEX
    Explanations

    the word "eager"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "eager" and its variations

    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
    section
    -0.67
    netflix
    -0.64
    yan
    -0.62
    sect
    -0.62
    facts
    -0.60
    zone
    -0.60
     damages
    -0.60
    strike
    -0.59
     Theft
    -0.59
    ocide
    -0.59
    POSITIVE LOGITS
     eager
    3.34
     anxious
    1.87
     eagerly
    1.77
     enthusiastic
    1.75
     keen
    1.73
     willing
    1.57
     reluctant
    1.55
     unwilling
    1.52
     ecstatic
    1.49
     itching
    1.46
    Activations Density 0.013%

    No Known Activations