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. 10-RES-JB
    6. 18244
    Prev
    Next
    INDEX
    Explanations

    words related to bridge

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "Br" in names and other terms

    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
    NESS
    -0.64
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.63
     acting
    -0.62
     AMERICA
    -0.62
     tweeting
    -0.62
     Relief
    -0.61
     terr
    -0.60
     Europa
    -0.60
     functioning
    -0.60
     Mercury
    -0.59
    POSITIVE LOGITS
    atton
    1.44
    acket
    1.40
    onson
    1.37
    idget
    1.31
    addock
    1.29
    ackets
    1.29
    anches
    1.27
    anson
    1.23
    anded
    1.20
    anca
    1.19
    Activations Density 0.012%

    No Known Activations