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. 18173
    Prev
    Next
    INDEX
    Explanations

    numerical values associated with different units of measurement, such as money per square foot or tons per person per year

    oai_token-act-pair · gpt-3.5-turbo

    metrics or measurements associated with quantities

    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
    soDeliveryDate
    -0.77
    POL
    -0.74
    bye
    -0.73
    bery
    -0.68
    forts
    -0.67
    iquid
    -0.66
    tymology
    -0.65
    bley
    -0.65
     archaeologists
    -0.64
    obbies
    -0.64
    POSITIVE LOGITS
     expenditure
    0.79
     basis
    0.74
    pection
    0.70
     increments
    0.70
     MHz
    0.68
     percentile
    0.67
    adelphia
    0.67
     per
    0.66
    imeter
    0.66
     outburst
    0.65
    Activations Density 0.063%

    No Known Activations