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. 532
    Prev
    Next
    INDEX
    Explanations

    phrases related to people or objects forming a line or queue

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "lining" or "lined" used in various contexts

    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
    CVE
    -0.80
    ILY
    -0.70
    ULT
    -0.68
     guiIcon
    -0.68
    reck
    -0.67
    ISSION
    -0.66
    EStream
    -0.64
    è¦ļéĨĴ
    -0.64
    ignty
    -0.63
    orean
    -0.63
    POSITIVE LOGITS
    ups
    0.86
    lines
    0.83
    arity
    0.80
    boxes
    0.75
    backer
    0.75
    up
    0.74
    comed
    0.73
    cro
    0.73
    roads
    0.70
    pherd
    0.68
    Activations Density 0.018%

    No Known Activations