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. 3-RES-JB
    6. 22190
    Prev
    Next
    INDEX
    Explanations

    operations or actions that are physically impactful or intense

    oai_token-act-pair · gpt-3.5-turbo

    words related to actions or activities that imply movement or completion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    REF
    -0.63
     UE
    -0.61
    ISH
    -0.60
    yss
    -0.59
     Narr
    -0.58
    اÙĦ
    -0.58
    LESS
    -0.58
     stewards
    -0.57
    âĸ¬
    -0.56
    SOURCE
    -0.55
    POSITIVE LOGITS
    paces
    1.43
    ettings
    1.40
    pace
    1.39
    creen
    1.32
    mith
    1.24
    omething
    1.23
    hift
    1.20
    hops
    1.19
    hips
    1.16
    peed
    1.13
    Activations Density 0.520%

    No Known Activations