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. 11-RES-JB
    6. 19177
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal and political situations

    oai_token-act-pair · gpt-3.5-turbo

    references to societal issues and challenges

    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
    respective
    -0.70
    wx
    -0.69
    \":
    -0.66
     Pwr
    -0.64
    depending
    -0.64
     Definitions
    -0.64
    ategor
    -0.64
    assuming
    -0.63
    prisingly
    -0.62
    é¾įåĸļ士
    -0.61
    POSITIVE LOGITS
     AIDS
    0.91
     malaria
    0.76
     Osama
    0.75
     chemotherapy
    0.74
     menstru
    0.71
     raping
    0.71
     tuberculosis
    0.70
     assass
    0.70
     underwear
    0.70
     JFK
    0.69
    Activations Density 1.630%

    No Known Activations