© 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. 9-RES-JB
    11. 18408
    Prev
    Next
    INDEX
    Explanations

    statistical information such as numbers and percentages

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and statistics related to events or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Strateg
    -0.77
    ocracy
    -0.76
    ourage
    -0.73
    ipedia
    -0.72
    tainment
    -0.71
    Ability
    -0.70
     aristocracy
    -0.69
    omics
    -0.68
     Translation
    -0.67
    Appearance
    -0.66
    POSITIVE LOGITS
     cases
    1.67
     incidents
    1.49
     instances
    1.47
     prosecutions
    1.27
     occurrences
    1.27
     complaints
    1.20
     occasions
    1.17
     violations
    1.14
     Cases
    1.13
     deaths
    1.13
    Activations Density 0.443%

    No Known Activations