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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 11835
    Prev
    Next
    INDEX
    Explanations

    technical terms related to construction or development

    oai_token-act-pair · gpt-3.5-turbo

    terms related to software or hardware builds and versions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    izon
    -0.86
    mia
    -0.85
     Lauder
    -0.77
    ican
    -0.75
    mic
    -0.73
    romeda
    -0.73
    ricular
    -0.68
    utical
    -0.68
    nton
    -0.67
    ppe
    -0.67
    POSITIVE LOGITS
    smanship
    0.76
    packs
    0.75
     decks
    0.73
    offs
    0.72
    raft
    0.70
     suspense
    0.70
    strap
    0.68
    built
    0.67
     builds
    0.67
     kits
    0.66
    Activations Density 0.033%

    No Known Activations