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. 11-RES-JB
    6. 18158
    Prev
    Next
    INDEX
    Explanations

    times expressed in the format of hours and minutes, such as "9:00 p.m."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the letter "m" in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    theless
    -0.66
     spare
    -0.56
     blink
    -0.54
    0000000000000000
    -0.53
     Carbuncle
    -0.53
     acknowled
    -0.53
     resists
    -0.53
     captcha
    -0.52
     Izan
    -0.52
     creep
    -0.51
    POSITIVE LOGITS
    .,
    1.73
    .;
    1.49
    .:
    1.48
    .?
    1.38
    .,"
    1.36
    .-
    1.28
    .—
    1.26
    ./
    1.24
    .–
    1.21
    .):
    1.18
    Activations Density 0.020%

    No Known Activations