© 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. 11-RES-JB
    11. 16442
    Prev
    Next
    INDEX
    Explanations

    instructions for preventing or solving issues related to specific objects or actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to prevention and safety measures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    truth
    -0.76
    ynchronous
    -0.75
     Canaver
    -0.74
    fam
    -0.72
    reon
    -0.72
     Neuroscience
    -0.70
     Rational
    -0.68
    ourses
    -0.68
    utics
    -0.67
    ortality
    -0.67
    POSITIVE LOGITS
     stains
    1.43
     leakage
    1.31
     irritation
    1.29
     corrosion
    1.28
     scratches
    1.28
     moisture
    1.27
     contaminants
    1.27
     contamination
    1.22
     buildup
    1.20
     oxidation
    1.20
    Activations Density 0.314%

    No Known Activations