© 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. 23265
    Prev
    Next
    INDEX
    Explanations

    instances where someone makes a promise or a commitment to do something

    oai_token-act-pair · gpt-3.5-turbo

    words related to commitments or promises, particularly in political or social contexts

    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
     sshd
    -0.83
    udic
    -0.73
     inferior
    -0.69
     intercept
    -0.64
    iga
    -0.63
     diagnostic
    -0.63
     classification
    -0.63
     intersection
    -0.62
     sorting
    -0.62
     filter
    -0.61
    POSITIVE LOGITS
     pledges
    3.24
     pledging
    2.64
    pled
    2.40
     pledge
    2.20
     pledged
    1.82
     vows
    1.70
     Pledge
    1.70
     manifesto
    1.46
     promises
    1.21
     commitments
    1.19
    Activations Density 0.028%

    No Known Activations