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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 13748
    Prev
    Next
    INDEX
    Explanations

    phrases related to activities or actions involving a specific person or group

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to significant events involving individuals or groups

    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
    DragonMagazine
    -0.66
    ļéĨĴ
    -0.61
    £ı
    -0.60
    assetsadobe
    -0.52
    emale
    -0.52
    ãĥ´
    -0.51
    idav
    -0.51
    wagon
    -0.49
    to
    -0.49
    Adds
    -0.48
    POSITIVE LOGITS
     quite
    0.54
     principally
    0.51
     namely
    0.51
     decidedly
    0.50
     fairly
    0.50
    .''.
    0.49
     either
    0.49
     extraordinarily
    0.48
     considerable
    0.48
    .
    0.47
    Activations Density 1.186%

    No Known Activations