© 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. 10165
    Prev
    Next
    INDEX
    Explanations

    keywords related to newsletter sign-ups

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to signing up or subscribing to services

    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
    alore
    -0.76
     shine
    -0.62
     gearing
    -0.57
    imer
    -0.57
     tatt
    -0.57
    abouts
    -0.57
     blazing
    -0.56
     creep
    -0.56
    nil
    -0.55
     pim
    -0.55
    POSITIVE LOGITS
    $$$$
    0.84
     Invalid
    0.78
     Required
    0.76
     Cancel
    0.72
     Slowly
    0.69
     Each
    0.68
     Enter
    0.68
     Failed
    0.67
     Accept
    0.66
     Reload
    0.66
    Activations Density 0.012%

    No Known Activations