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. 15242
    Prev
    Next
    INDEX
    Explanations

    physical actions or movements related to struggling or grappling

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

    action verbs that convey movement or physical interactions

    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
     mosqu
    -0.72
     Fiji
    -0.70
    SPONSORED
    -0.66
    ãĥīãĥ©ãĤ´ãĥ³
    -0.65
     artif
    -0.64
     Pir
    -0.64
     America
    -0.62
     explo
    -0.61
    ãĤ¤
    -0.61
     Âł Âł Âł Âł
    -0.61
    POSITIVE LOGITS
    ling
    2.49
    led
    2.34
    les
    2.31
    lers
    2.00
    lings
    1.80
    ler
    1.77
    lement
    1.74
    lements
    1.58
    ernaut
    1.51
    lest
    1.48
    Activations Density 0.107%

    No Known Activations