© 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. 6-RES-JB
    11. 970
    Prev
    Next
    INDEX
    Explanations

    words related to crime and law enforcement

    oai_token-act-pair · gpt-3.5-turbo

    evaluations of artistic quality and effectiveness in storytelling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     contracted
    -0.88
     notified
    -0.76
     contracting
    -0.71
     donated
    -0.71
     healed
    -0.71
     declined
    -0.70
    hower
    -0.70
     nearby
    -0.69
    rollment
    -0.68
    profit
    -0.68
    POSITIVE LOGITS
     understatement
    0.97
     Subtle
    0.93
     tropes
    0.92
     cinematic
    0.91
     subtle
    0.90
     downright
    0.88
     Pengu
    0.88
     realism
    0.86
     storytelling
    0.85
     gimm
    0.84
    Activations Density 1.181%

    No Known Activations