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. 6188
    Prev
    Next
    INDEX
    Explanations

    numerical quantities, specifically quantities that indicate a specific count or amount

    oai_token-act-pair · gpt-3.5-turbo

    repeated occurrences of the phrase "at" followed by a numerical value or a reference to time

    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
    FTWARE
    -0.73
    aceutical
    -0.68
    powder
    -0.65
    clean
    -0.64
    alpha
    -0.63
    Tube
    -0.61
    adoes
    -0.61
    tools
    -0.60
     thereof
    -0.59
    monkey
    -0.57
    POSITIVE LOGITS
     least
    1.16
    mosp
    1.03
    hens
    0.93
    kinson
    0.89
     times
    0.88
    chieve
    0.86
    onement
    0.80
    ention
    0.79
    roph
    0.78
    £ı
    0.76
    Activations Density 0.085%

    No Known Activations