© 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. 20470
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical locations and establishments

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating ownership or association

    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
     chops
    -0.83
     buildup
    -0.79
     gears
    -0.78
     pieces
    -0.78
    issions
    -0.77
     deployments
    -0.76
     deserts
    -0.74
     ears
    -0.73
    uria
    -0.72
     gaps
    -0.70
    POSITIVE LOGITS
     Senator
    0.98
     disgr
    0.92
     Representative
    0.86
    interstitial
    0.84
     Sir
    0.84
     Congressman
    0.82
     Gov
    0.80
     Mrs
    0.79
     Colonel
    0.78
     President
    0.78
    Activations Density 0.224%

    No Known Activations