© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 9423
    Prev
    Next
    INDEX
    Explanations

    numerical values in the context of quantities or costs

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and measurements related to costs and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ressor
    -0.69
     Participant
    -0.63
     Played
    -0.63
    Reviewer
    -0.62
    £ı
    -0.62
     vanquished
    -0.60
    actor
    -0.59
    llor
    -0.58
     Fallen
    -0.58
     Collider
    -0.56
    POSITIVE LOGITS
    %
    1.11
    %-
    1.10
     cents
    1.08
    ¢
    1.07
     percent
    1.06
    ½
    1.02
     watts
    0.97
    ÃĹ
    0.95
    %.
    0.95
     million
    0.90
    Activations Density 0.273%

    No Known Activations