© 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. 9-RES-JB
    11. 14213
    Prev
    Next
    INDEX
    Explanations

    words related to behavior, specifically polite and reserved actions

    oai_token-act-pair · gpt-3.5-turbo

    references to social behavior and manners

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     HUGE
    -0.83
    !!!!!
    -0.81
    !!!!
    -0.79
    initely
    -0.78
     UPDATE
    -0.77
     START
    -0.75
    ANA
    -0.72
     TRUMP
    -0.72
    !!!
    -0.71
     Lets
    -0.71
    POSITIVE LOGITS
     scorn
    1.00
     indign
    0.93
     unworthy
    0.91
     indisc
    0.90
     betray
    0.88
     fleeting
    0.85
     arist
    0.84
     treacher
    0.83
     griev
    0.82
     disappro
    0.82
    Activations Density 1.416%

    No Known Activations