© 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. 2-RES-JB
    11. 1427
    Prev
    Next
    INDEX
    Explanations

    verbs related to opposition or defiance

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "resist" and its variations related to opposition or defiance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ammy
    -0.87
    =-=-=-=-=-=-=-=-
    -0.83
    weekly
    -0.76
    posted
    -0.70
     Roads
    -0.69
    operated
    -0.69
    âĹ¼
    -0.68
    company
    -0.67
     Bohem
    -0.67
    day
    -0.67
    POSITIVE LOGITS
     resist
    1.14
     resistance
    1.05
     resisting
    0.98
     resisted
    0.95
     resists
    0.93
     Resist
    0.88
    ances
    0.85
    encia
    0.82
    ency
    0.78
     resistant
    0.74
    Activations Density 0.008%

    No Known Activations