© 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. 1292
    Prev
    Next
    INDEX
    Explanations

    sentences related to news stories or events

    oai_token-act-pair · gpt-3.5-turbo

    references to crimes or criminal activities

    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
     consolidate
    -0.94
     reserves
    -0.83
     consolid
    -0.81
    uity
    -0.81
     synerg
    -0.80
     refine
    -0.76
     foregoing
    -0.75
     evolve
    -0.75
     forecasting
    -0.73
     unified
    -0.73
    POSITIVE LOGITS
    VICE
    1.05
    Owner
    0.90
    Interested
    0.89
    Anonymous
    0.89
    Laura
    0.89
    FACE
    0.87
    Marie
    0.84
    Daniel
    0.84
    Roy
    0.84
    von
    0.83
    Activations Density 0.353%

    No Known Activations