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. 7-RES-JB
    6. 3327
    Prev
    Next
    INDEX
    Explanations

    terms related to philanthropy and sports goaltending

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with philanthropy and goaltending

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Shack
    -0.71
     Improvement
    -0.69
     tune
    -0.67
     Feast
    -0.67
     Dome
    -0.66
     Maid
    -0.65
     bearer
    -0.65
     Cultural
    -0.61
    WARD
    -0.60
     Diver
    -0.60
    POSITIVE LOGITS
    ancies
    1.11
    gments
    1.10
    hett
    1.04
    itures
    1.03
    itors
    1.01
    elines
    1.00
    aces
    0.99
    ues
    0.97
    itions
    0.97
    acies
    0.96
    Activations Density 0.143%

    No Known Activations