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. 9-RES-JB
    6. 289
    Prev
    Next
    INDEX
    Explanations

    verbs related to influencing or persuading others

    oai_token-act-pair · gpt-3.5-turbo

    words related to persuasion or attempts to influence others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    practice
    -0.72
    eatures
    -0.71
     largeDownload
    -0.71
    emale
    -0.70
    ateral
    -0.65
    bard
    -0.64
     Accessed
    -0.64
    imb
    -0.63
    abytes
    -0.63
    alm
    -0.63
    POSITIVE LOGITS
     skeptics
    0.86
     reluctant
    0.84
    ingly
    0.78
    ments
    0.75
    tale
    0.75
     convinc
    0.73
     voters
    0.72
     otherwise
    0.72
     gull
    0.72
     convince
    0.72
    Activations Density 0.040%

    No Known Activations