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. 15038
    Prev
    Next
    INDEX
    Explanations

    sports-related terms and statistics

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

    negative numerical values typically related to performance metrics

    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
     exha
    -1.42
     millenn
    -1.40
     metic
    -1.38
     referen
    -1.27
     eleph
    -1.25
     behavi
    -1.24
     tremend
    -1.23
     unden
    -1.19
     proport
    -1.19
     nodd
    -1.18
    POSITIVE LOGITS
    0
    1.58
    4
    1.46
    1
    1.45
    5
    1.44
    3
    1.43
    2
    1.42
    6
    1.42
    8
    1.39
    7
    1.37
    9
    1.37
    Activations Density 0.034%

    No Known Activations