Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 5-RES-JB
    6. 1894
    Prev
    Next
    INDEX
    Explanations

    times expressed in hours with the specific time, such as "eight o'clock" or "ten o'clock."

    oai_token-act-pair · gpt-3.5-turbo

    references to time, particularly clock times

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sels
    -0.83
    du
    -0.78
    shared
    -0.72
    ebook
    -0.72
    sche
    -0.71
    ifferent
    -0.69
    itably
    -0.69
    won
    -0.67
    Sov
    -0.67
     Schwar
    -0.67
    POSITIVE LOGITS
    wise
    0.93
    urnal
    0.87
    inois
    0.87
    iculty
    0.85
    ayson
    0.83
    agascar
    0.79
    ousand
    0.76
    CLASSIFIED
    0.74
     vigil
    0.73
    uminati
    0.71
    Activations Density 0.022%

    No Known Activations