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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 14307
    Prev
    Next
    INDEX
    Explanations

    words related to willingness or readiness

    oai_token-act-pair · gpt-3.5-turbo

    expressions of willingness or readiness to take action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Anthem
    -0.87
    hemy
    -0.79
    our
    -0.76
    isol
    -0.72
    alien
    -0.71
    rx
    -0.70
    Champ
    -0.69
    hem
    -0.69
    design
    -0.68
    gran
    -0.68
    POSITIVE LOGITS
    theless
    0.87
     enough
    0.81
     gladly
    0.78
     willing
    0.74
     lend
    0.73
    terday
    0.73
     unres
    0.70
     willingly
    0.70
     unden
    0.68
     rent
    0.68
    Activations Density 0.028%

    No Known Activations