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. 7-RES-JB
    6. 7033
    Prev
    Next
    INDEX
    Explanations

    expressions of desire or preference

    oai_token-act-pair · gpt-3.5-turbo

    expressions of desire or preference

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cies
    -0.73
    hemy
    -0.65
    ibles
    -0.62
    onut
    -0.61
    ionic
    -0.60
    ivities
    -0.60
    ongh
    -0.60
    ilian
    -0.59
    cial
    -0.58
    inas
    -0.58
    POSITIVE LOGITS
     someday
    0.85
     sooner
    0.70
     Roses
    0.68
     if
    0.67
     anytime
    0.64
    ij士
    0.64
    course
    0.63
     ACTIONS
    0.61
     Wouldn
    0.61
    imaru
    0.60
    Activations Density 0.130%

    No Known Activations