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. 1987
    Prev
    Next
    INDEX
    Explanations

    text related to serious matters or issues

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "serious."

    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
    atu
    -0.83
    tein
    -0.77
    eez
    -0.77
    ucky
    -0.75
    wright
    -0.73
     Tycoon
    -0.72
    enaries
    -0.72
    orius
    -0.66
    hops
    -0.65
    orious
    -0.65
    POSITIVE LOGITS
    lly
    0.95
    serious
    0.92
     serious
    0.87
     dent
    0.80
     enough
    0.79
    nces
    0.77
    mond
    0.75
    itar
    0.75
    enough
    0.74
     consideration
    0.74
    Activations Density 0.023%

    No Known Activations