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. 4-RES-JB
    6. 23743
    Prev
    Next
    INDEX
    Explanations

    references to famous individuals

    oai_token-act-pair · gpt-3.5-turbo

    specific proper nouns and notable entities related to history, media, and significant events

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

    No Comments

    Negative Logits
    actionDate
    -0.58
    href
    -0.54
    ãĤ¤ãĥĪ
    -0.50
    é¾įåĸļ士
    -0.50
    NAS
    -0.49
    Reviewer
    -0.47
    YN
    -0.47
    RAW
    -0.46
    hillary
    -0.46
    PATH
    -0.44
    POSITIVE LOGITS
     fiasco
    0.53
     intervened
    0.50
     imitation
    0.48
    enko
    0.48
    eers
    0.48
    hler
    0.47
    culosis
    0.46
     fame
    0.45
     debacle
    0.44
    arettes
    0.44
    Activations Density 1.205%

    No Known Activations