© 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. 8-RES-JB
    11. 17257
    Prev
    Next
    INDEX
    Explanations

    phrases related to governmental committees and investigations

    oai_token-act-pair · gpt-3.5-turbo

    references to committees and their related actions or topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     scoop
    -0.77
     siph
    -0.73
     finger
    -0.71
     crate
    -0.70
     fetch
    -0.68
     pump
    -0.67
     glue
    -0.67
     buckets
    -0.67
     hone
    -0.66
    oland
    -0.65
    POSITIVE LOGITS
     Aging
    1.17
     behalf
    0.87
     Disability
    0.84
     Radiation
    0.84
     Settlement
    0.83
     Standards
    0.83
     Exercise
    0.82
     Enh
    0.82
     Principles
    0.81
     Drugs
    0.79
    Activations Density 0.044%

    No Known Activations