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. 8740
    Prev
    Next
    INDEX
    Explanations

    domain names

    oai_token-act-pair · gpt-3.5-turbo

    terms related to common names (CN) and designated names (DN) in a trademark or internet context

    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
    minster
    -0.77
    eer
    -0.77
    gerald
    -0.76
    Keefe
    -0.74
    eers
    -0.73
    à©
    -0.71
    ters
    -0.68
    makers
    -0.67
    lington
    -0.66
    deen
    -0.66
    POSITIVE LOGITS
    emonic
    1.03
    avez
    0.94
    é¾
    0.93
    ascar
    0.89
    anguage
    0.82
    plain
    0.82
    alogy
    0.81
    umbn
    0.80
    uggets
    0.79
    eny
    0.79
    Activations Density 0.030%

    No Known Activations