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. 4-RES-JB
    6. 7772
    Prev
    Next
    INDEX
    Explanations

    phrases expressing anticipation or expectation

    oai_token-act-pair · gpt-3.5-turbo

    expressions of anticipation or eagerness about future events

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

    No Comments

    Negative Logits
     Manson
    -0.65
     Lack
    -0.61
    outing
    -0.61
    hiba
    -0.60
    outed
    -0.59
    AKING
    -0.59
    cius
    -0.59
     Freeman
    -0.59
    omsky
    -0.59
    hem
    -0.58
    POSITIVE LOGITS
    WARD
    0.90
    ï¸
    0.87
     puberty
    0.79
    wards
    0.73
    actionDate
    0.69
    comings
    0.68
     nostalg
    0.67
    imately
    0.67
    ward
    0.65
    wcs
    0.65
    Activations Density 0.011%

    No Known Activations