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. 1-RES-JB
    6. 19036
    Prev
    Next
    INDEX
    Explanations

    references to the location "Laguna"

    oai_token-act-pair · gpt-3.5-turbo

    references to the location "Laguna."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Publisher
    -0.75
    Pages
    -0.72
    pages
    -0.72
    txt
    -0.70
    IJ
    -0.67
    drivers
    -0.67
    scl
    -0.66
     Measures
    -0.65
    Ń
    -0.64
    tons
    -0.63
    POSITIVE LOGITS
    uthor
    1.38
    una
    1.23
    ña
    0.98
    ushi
    0.89
    igi
    0.86
    velength
    0.85
    vati
    0.83
    issan
    0.83
    apon
    0.79
    uria
    0.79
    Activations Density 0.005%

    No Known Activations