© 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 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. 4-RES-JB
    11. 4856
    Prev
    Next
    INDEX
    Explanations

    names or terms related to certain individuals or places

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific surname, particularly "Field."

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

    No Comments

    Negative Logits
    ILA
    -0.94
    externalActionCode
    -0.89
     millenn
    -0.85
    ccording
    -0.85
     unden
    -0.80
     undermin
    -0.79
    Magikarp
    -0.78
     recip
    -0.78
    ailability
    -0.76
     conflic
    -0.73
    POSITIVE LOGITS
    field
    1.04
    fields
    0.85
    er
    0.77
     Junction
    0.77
    ridge
    0.76
     Marshal
    0.73
    wood
    0.73
    hurst
    0.73
     Yards
    0.73
    notes
    0.72
    Activations Density 0.010%

    No Known Activations