Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 3782
    Prev
    Next
    INDEX
    Explanations

    instances where the action of discussing something occurs

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "discuss" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sucker
    -0.64
     Inst
    -0.63
     outp
    -0.59
     sadd
    -0.58
     Lucky
    -0.57
     jack
    -0.57
     Balloon
    -0.56
     lucky
    -0.56
    +
    -0.55
     Lif
    -0.55
    POSITIVE LOGITS
     discuss
    3.27
     discussing
    2.14
     discusses
    2.10
     discussed
    1.92
     Discuss
    1.87
     talk
    1.79
    Discuss
    1.67
     discussion
    1.58
     speculate
    1.49
    talk
    1.45
    Activations Density 0.016%

    No Known Activations