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. 10-RES-JB
    6. 22848
    Prev
    Next
    INDEX
    Explanations

    words associated with the action of approaching someone or something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "approach" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pite
    -0.78
    runs
    -0.76
    cell
    -0.73
    claimer
    -0.68
    marine
    -0.68
    bel
    -0.68
    fre
    -0.67
    extra
    -0.67
    rats
    -0.66
    ãĥ©ãĥ³
    -0.66
    POSITIVE LOGITS
     cautiously
    0.80
     puberty
    0.80
     intersections
    0.68
     Ceres
    0.67
     adulthood
    0.66
    isition
    0.61
    ingly
    0.61
     kindred
    0.61
     adolescence
    0.60
     strangers
    0.60
    Activations Density 0.051%

    No Known Activations