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

    Neuronpedia

    APICircuit 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. 4-RES-JB
    6. 5193
    Prev
    Next
    INDEX
    Explanations

    phrases related to power or strength

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Power."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¢ãĥ«
    -0.78
    ead
    -0.70
     seq
    -0.69
    oslov
    -0.67
    arians
    -0.65
    olson
    -0.65
    ript
    -0.63
    romeda
    -0.63
    ×IJ
    -0.63
    eryl
    -0.63
    POSITIVE LOGITS
     Rangers
    0.83
     Grid
    0.82
    puff
    0.79
    bilt
    0.77
    Tap
    0.76
    stroke
    0.76
    houses
    0.75
    ivot
    0.75
    Points
    0.74
     Generation
    0.74
    Activations Density 0.011%

    No Known Activations