© 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. 8-RES-JB
    11. 4604
    Prev
    Next
    INDEX
    Explanations

    instances of sentences ending with the word "when"

    oai_token-act-pair · gpt-3.5-turbo

    instances of "when" indicating conditional or temporal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awar
    -0.72
    hack
    -0.70
    tip
    -0.68
    vantage
    -0.67
    ilan
    -0.67
    yp
    -0.67
    vari
    -0.66
    oire
    -0.66
    ve
    -0.66
    fighter
    -0.65
    POSITIVE LOGITS
     they
    0.79
     nobody
    0.75
     compared
    0.72
     everyone
    0.72
     there
    0.71
     everybody
    0.69
     THEY
    0.69
     we
    0.69
     simultaneously
    0.67
     expecting
    0.66
    Activations Density 0.118%

    No Known Activations