© 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. 7-RES-JB
    11. 23971
    Prev
    Next
    INDEX
    Explanations

    neighborhood-related words and details

    oai_token-act-pair · gpt-3.5-turbo

    references to neighbors and residents involved in community incidents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hegemony
    -0.82
    NSA
    -0.77
    inventoryQuantity
    -0.70
    acity
    -0.65
    ãĥ¯
    -0.65
     superpower
    -0.65
     presidency
    -0.64
    Winner
    -0.63
     trillion
    -0.63
     monopoly
    -0.62
    POSITIVE LOGITS
     chanted
    1.09
     allege
    0.98
     evacuated
    0.95
     mourn
    0.92
     protested
    0.90
     hurled
    0.89
     gathered
    0.89
     erupted
    0.87
     complained
    0.86
    folk
    0.85
    Activations Density 0.361%

    No Known Activations