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. 6-RES-JB
    6. 8306
    Prev
    Next
    INDEX
    Explanations

    instances of the number "two" in close proximity

    oai_token-act-pair · gpt-3.5-turbo

    instances of duality or pairs in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    heimer
    -0.60
     fears
    -0.58
     Schultz
    -0.57
    icit
    -0.56
     Hastings
    -0.54
     cynicism
    -0.54
    partisan
    -0.52
    humane
    -0.52
     demoral
    -0.52
     retribution
    -0.52
    POSITIVE LOGITS
     apiece
    1.07
     respective
    0.79
     optionally
    0.73
     respectively
    0.73
     equivalents
    0.69
     consecut
    0.69
     interchangeable
    0.69
     varying
    0.68
     randomly
    0.67
     grouped
    0.67
    Activations Density 1.492%

    No Known Activations