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. 17936
    Prev
    Next
    INDEX
    Explanations

    the word "line" followed by a numerical value

    oai_token-act-pair · gpt-3.5-turbo

    references to "lines" in various contexts

    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
    CVE
    -0.76
    JUST
    -0.65
    代
    -0.64
    sylvania
    -0.64
    âĺħâĺħ
    -0.62
     Jarrett
    -0.60
    sburg
    -0.57
     salts
    -0.57
    Mos
    -0.56
    lishing
    -0.56
    POSITIVE LOGITS
    ups
    1.41
    backer
    1.31
    up
    1.09
    ages
    1.08
    aments
    1.06
    breaks
    0.93
    break
    0.86
    breaking
    0.84
    feed
    0.81
    breakers
    0.81
    Activations Density 0.038%

    No Known Activations