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. 17737
    Prev
    Next
    INDEX
    Explanations

    information relating to ice hockey players and their stats

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

    information related to hockey player statistics and drafts

    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
    $$$$
    -0.79
    xual
    -0.79
     Saban
    -0.74
    Bey
    -0.72
     Goodell
    -0.71
     miscar
    -0.70
    Moon
    -0.69
     Rove
    -0.69
     Nile
    -0.68
    CVE
    -0.66
    POSITIVE LOGITS
     AHL
    1.39
     defenseman
    1.16
     NHL
    1.15
    HL
    1.13
     goaltender
    1.11
     skating
    1.10
     goalt
    1.10
     Hockey
    1.07
    monton
    1.07
     Canucks
    1.04
    Activations Density 0.292%

    No Known Activations