© 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. 1269
    Prev
    Next
    INDEX
    Explanations

    people or groups involved in criminal activities

    oai_token-act-pair · gpt-3.5-turbo

    references to groups of individuals, particularly those involved in social issues or conflicts

    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
    à¤
    -0.72
    inventoryQuantity
    -0.71
    ":"/
    -0.70
    Market
    -0.70
    osterone
    -0.68
     repertoire
    -0.65
    fff
    -0.63
     Reign
    -0.63
     Carnage
    -0.61
    ãĤ¦
    -0.61
    POSITIVE LOGITS
     who
    0.94
     apiece
    0.92
    hips
    0.90
     boarded
    0.89
     together
    0.86
     abducted
    0.86
     kidnapped
    0.85
     whom
    0.85
     dressed
    0.84
     crammed
    0.83
    Activations Density 0.245%

    No Known Activations