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. 12-RES-JB
    6. 17750
    Prev
    Next
    INDEX
    Explanations

    words related to sports teams

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to the word "Burnley" or related to events and entities associated with it, particularly in sports contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
    kson
    -0.69
     Heavenly
    -0.61
     Archangel
    -0.61
    DonaldTrump
    -0.56
    prises
    -0.54
    ------------------------------------------------
    -0.54
    ilial
    -0.53
     Allaah
    -0.53
     NETWORK
    -0.52
    ional
    -0.52
    POSITIVE LOGITS
    aby
    1.18
    ished
    1.05
    side
    1.04
    ham
    1.02
    ey
    0.96
    ley
    0.87
    emouth
    0.84
    ishing
    0.84
    zie
    0.81
    lett
    0.78
    Activations Density 0.097%

    No Known Activations