© 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. 6296
    Prev
    Next
    INDEX
    Explanations

    instances of willingness to do something

    oai_token-act-pair · gpt-3.5-turbo

    the concept of willingness or openness to take action

    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
    ital
    -0.72
    inth
    -0.70
    raud
    -0.64
     CLASS
    -0.63
     Gren
    -0.62
     Digest
    -0.61
     Lag
    -0.60
    izz
    -0.60
    Cast
    -0.60
     lag
    -0.59
    POSITIVE LOGITS
     willing
    3.52
     unwilling
    2.30
     willingness
    1.76
     eager
    1.58
     reluctant
    1.57
     receptive
    1.42
     interested
    1.41
     willingly
    1.39
     capable
    1.32
     hesitant
    1.28
    Activations Density 0.008%

    No Known Activations