© 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. 9295
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the necessity of taking specific actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating obligations or actions to improve safety and compliance

    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
    told
    -0.91
    didn
    -0.79
    hot
    -0.75
     popped
    -0.75
    ooked
    -0.74
     begged
    -0.74
     yelled
    -0.74
     snapped
    -0.73
    Cooldown
    -0.71
    fle
    -0.70
    POSITIVE LOGITS
     minimize
    1.49
     mitigate
    1.47
     maximize
    1.41
     facilitate
    1.39
     ensure
    1.39
     achieve
    1.36
     enhance
    1.35
     safeguard
    1.31
     assure
    1.26
     comply
    1.23
    Activations Density 0.251%

    No Known Activations