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. 5492
    Prev
    Next
    INDEX
    Explanations

    terms related to technology and computing concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to various mathematical concepts and their applications

    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
     Category
    -0.81
     Pillar
    -0.79
     Plaintiff
    -0.78
     Hour
    -0.77
     Doe
    -0.72
     panties
    -0.71
     Month
    -0.71
     Fifth
    -0.71
     Display
    -0.70
     disadvant
    -0.69
    POSITIVE LOGITS
    ro
    1.17
    rol
    1.08
    rosc
    1.07
    achy
    1.04
    ros
    1.04
    raq
    1.03
    rans
    1.02
    rology
    0.99
    ãĤ·ãĥ£
    0.96
    bol
    0.94
    Activations Density 0.260%

    No Known Activations