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. 9-RES-JB
    6. 22351
    Prev
    Next
    INDEX
    Explanations

    actions related to violence

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate actions or intentions related to "to" phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Observer
    -0.63
     Bhar
    -0.60
     Parameters
    -0.60
     employer
    -0.59
     Trek
    -0.59
     traveller
    -0.59
     IR
    -0.59
     Country
    -0.57
     traveler
    -0.55
     franch
    -0.54
    POSITIVE LOGITS
     commemorate
    1.28
    pless
    1.13
     simulate
    1.12
     alleviate
    1.11
     celebrate
    1.09
     relieve
    1.07
     signify
    1.06
    wered
    1.04
    asted
    1.04
     emphasize
    1.03
    Activations Density 0.230%

    No Known Activations