© 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. 2-RES-JB
    11. 8302
    Prev
    Next
    INDEX
    Explanations

    instances where someone is ready or prepared to do something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "willing."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alien
    -0.78
     Anthem
    -0.78
    ORGE
    -0.71
    gran
    -0.68
    ECH
    -0.67
    arrow
    -0.67
    adish
    -0.67
    older
    -0.67
    APH
    -0.66
    ogg
    -0.66
    POSITIVE LOGITS
     willing
    1.04
    theless
    0.91
     unwilling
    0.90
     willingly
    0.82
     incent
    0.79
     gladly
    0.77
    terday
    0.76
     lend
    0.76
     unres
    0.75
     willingness
    0.75
    Activations Density 0.013%

    No Known Activations