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. 8-RES-JB
    6. 21303
    Prev
    Next
    INDEX
    Explanations

    features related to expressing personal goals or aspirations towards achievement or competition

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "of" indicating a relationship or connection among ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dayName
    -0.71
    blance
    -0.63
    illac
    -0.63
    irs
    -0.62
    assembly
    -0.61
    gage
    -0.58
    nes
    -0.57
    OGR
    -0.57
    overe
    -0.57
    gee
    -0.56
    POSITIVE LOGITS
     sudden
    0.83
     us
    0.74
     humanity
    0.74
    THING
    0.71
     humankind
    0.68
    udes
    0.66
    ahu
    0.65
    iev
    0.63
     these
    0.63
     imaginable
    0.62
    Activations Density 0.074%

    No Known Activations