Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 12704
    Prev
    Next
    INDEX
    Explanations

    verbs indicating a promise or commitment

    oai_token-act-pair · gpt-3.5-turbo

    instances of commitments or promises to take specific actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ther
    -0.79
    nesota
    -0.75
    awk
    -0.74
    apple
    -0.69
    Statistics
    -0.69
    apy
    -0.68
    dos
    -0.68
    Else
    -0.67
    othy
    -0.67
    iris
    -0.66
    POSITIVE LOGITS
     pledges
    1.22
     pledged
    1.15
     pledging
    1.14
     pledge
    1.05
     allegiance
    0.91
     commitments
    0.84
     commits
    0.77
     delegates
    0.75
    legates
    0.75
    xual
    0.75
    Activations Density 0.007%

    No Known Activations