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. 11-RES-JB
    6. 4574
    Prev
    Next
    INDEX
    Explanations

    references to countries

    oai_token-act-pair · gpt-3.5-turbo
    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
     Velocity
    -0.70
    omething
    -0.70
    Visual
    -0.70
    inventoryQuantity
    -0.64
    ocry
    -0.64
    uggest
    -0.63
    wered
    -0.61
    POSE
    -0.61
    Operation
    -0.60
    istant
    -0.60
    POSITIVE LOGITS
    wide
    1.41
    men
    1.32
    manship
    0.99
    side
    0.97
    man
    0.95
    spe
    0.91
    hood
    0.90
    maker
    0.89
    's
    0.89
    woman
    0.88
    Activations Density 0.072%

    No Known Activations