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. 20768
    Prev
    Next
    INDEX
    Explanations

    the concept of "the first" in a sequence or group

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate ordinal positions or sequences

    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
    rider
    -0.67
    matter
    -0.66
    body
    -0.62
    æ³
    -0.59
    ãĤ©
    -0.57
    Crime
    -0.57
    uction
    -0.56
    gow
    -0.56
    <?
    -0.55
    ļéĨĴ
    -0.55
    POSITIVE LOGITS
    uits
    0.83
    ©¶æ
    0.70
    ounds
    0.68
    ruits
    0.68
    icial
    0.67
     installments
    0.66
    sever
    0.64
    ensibly
    0.63
    oya
    0.63
    many
    0.62
    Activations Density 0.077%

    No Known Activations