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. 10-RES-JB
    6. 23779
    Prev
    Next
    INDEX
    Explanations

    numerical or alphanumerical patterns involving dashes or slashes

    oai_token-act-pair · gpt-3.5-turbo

    phrases that start with "by" followed by a number or a descriptor

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    idad
    -0.62
    اÙĦ
    -0.59
    SPONSORED
    -0.58
    igrate
    -0.55
    ãĥ´ãĤ¡
    -0.54
     Escape
    -0.53
    qqa
    -0.53
    auri
    -0.52
    isable
    -0.52
    Finish
    -0.52
    POSITIVE LOGITS
    products
    1.23
    product
    1.10
    pass
    1.03
    laws
    1.02
    akuya
    0.92
    tes
    0.91
    catch
    0.89
    election
    0.89
    law
    0.85
    stand
    0.82
    Activations Density 0.048%

    No Known Activations