© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 12325
    Prev
    Next
    INDEX
    Explanations

    terms related to controversial or provocative topics

    oai_token-act-pair · gpt-3.5-turbo

    derogatory or negative terms related to behavior and lifestyle

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Comprehensive
    -0.77
     Strategic
    -0.75
     Participant
    -0.71
     jointly
    -0.70
     Blueprint
    -0.69
     Pwr
    -0.68
     Investigative
    -0.68
     representative
    -0.66
     Executive
    -0.66
     Fiscal
    -0.66
    POSITIVE LOGITS
     boobs
    1.15
    cakes
    1.03
     tits
    1.01
    wolves
    0.99
    bugs
    0.98
    worms
    0.97
    balls
    0.96
    berries
    0.96
    cats
    0.95
     cakes
    0.94
    Activations Density 0.535%

    No Known Activations