Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 16038
    Prev
    Next
    INDEX
    Explanations

    specific numerical information, such as dates, amounts, or statistics

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to approval and compliance in social 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
    aturdays
    -0.51
     <-
    -0.49
    ãĥ¯ãĥ³
    -0.48
    alloween
    -0.46
    ãĥ¼ãĥĨãĤ£
    -0.46
    Ô
    -0.45
     Peyton
    -0.45
    bably
    -0.45
    _-
    -0.45
    iPhone
    -0.44
    POSITIVE LOGITS
    )."
    2.23
    .")
    2.20
    .""
    2.05
    ."
    2.05
    ."[
    2.04
    ".
    2.03
    )",
    2.02
     ..."
    2.02
    .",
    2.01
    )"
    2.00
    Activations Density 1.219%

    No Known Activations