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. 8-RES-JB
    6. 18086
    Prev
    Next
    INDEX
    Explanations

    differences between various entities or concepts

    oai_token-act-pair · gpt-3.5-turbo

    the concept of "difference" in various 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
    ihilation
    -0.83
    bye
    -0.76
    ãĤ¡
    -0.73
    din
    -0.73
    dn
    -0.72
    ERN
    -0.72
    avascript
    -0.72
    unc
    -0.71
    Closure
    -0.71
    igion
    -0.70
    POSITIVE LOGITS
     sexes
    1.04
     genders
    0.98
     eras
    0.81
     those
    0.76
     these
    0.74
     them
    0.73
     what
    0.68
     comparing
    0.67
     halves
    0.66
     sender
    0.65
    Activations Density 0.064%

    No Known Activations