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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & 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. 12603
    Prev
    Next
    INDEX
    Explanations

    phrases with a specific structure involving commas

    oai_token-act-pair · gpt-3.5-turbo

    enumerations or lists of topics or items being discussed

    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
    emaker
    -0.63
    oto
    -0.62
    ail
    -0.61
     recy
    -0.60
     bank
    -0.58
    ©¶æ
    -0.57
     idle
    -0.56
    ulic
    -0.55
     120
    -0.55
    ega
    -0.55
    POSITIVE LOGITS
    particularly
    0.81
    comings
    0.79
     namely
    0.76
    ãĥ´ãĤ¡
    0.76
     Pengu
    0.73
     EntityItem
    0.73
     Pastebin
    0.69
    especially
    0.68
     Practices
    0.68
     topics
    0.67
    Activations Density 0.851%

    No Known Activations