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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 24456
    Prev
    Next
    INDEX
    Explanations

    mentions of criminal activities and suspects

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals and their actions or conditions in an event narrative

    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
     Dominion
    -0.68
     Optim
    -0.65
     Racial
    -0.64
    Interest
    -0.63
     Definitions
    -0.63
     Watching
    -0.62
     Worlds
    -0.61
     Dusk
    -0.60
     Kids
    -0.60
     Romantic
    -0.60
    POSITIVE LOGITS
    'd
    1.16
     underwent
    1.07
     testified
    1.02
     fled
    1.00
     pleaded
    1.00
    aped
    0.98
     withdrew
    0.97
    zbollah
    0.97
    eded
    0.96
     wore
    0.94
    Activations Density 0.301%

    No Known Activations