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. 10-RES-JB
    6. 17043
    Prev
    Next
    INDEX
    Explanations

    past tense verbs related to movement

    oai_token-act-pair · gpt-3.5-turbo

    verbs related to movement or action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Confederation
    -0.69
    ament
    -0.68
    ullah
    -0.60
     Inher
    -0.60
    asio
    -0.58
     appell
    -0.58
    benef
    -0.57
     Abrams
    -0.56
    heed
    -0.56
     Insp
    -0.55
    POSITIVE LOGITS
    ggle
    1.07
     overboard
    1.07
     downstairs
    1.03
     upstairs
    1.03
    lems
    1.00
     unnoticed
    0.99
     nuts
    0.91
     ballistic
    0.91
     limp
    0.86
    og
    0.85
    Activations Density 0.073%

    No Known Activations