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. 8976
    Prev
    Next
    INDEX
    Explanations

    people's names that start with "Bro"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Bro" 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
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.62
     Nadu
    -0.61
     spirited
    -0.58
     retri
    -0.58
     scattered
    -0.58
    lessness
    -0.57
     fragmented
    -0.57
     Centauri
    -0.57
     Spectre
    -0.57
     chrome
    -0.56
    POSITIVE LOGITS
    ccoli
    1.42
    oks
    1.36
    die
    1.26
    dy
    1.23
    oke
    1.21
    okes
    1.18
    oking
    1.15
    yles
    1.14
    gue
    1.14
    thel
    1.12
    Activations Density 0.028%

    No Known Activations