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. 11-RES-JB
    6. 8706
    Prev
    Next
    INDEX
    Explanations

    mentions of criminal activities related to gangs

    oai_token-act-pair · gpt-3.5-turbo

    references to gang-related activities and violence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
    etsk
    -0.73
     Osh
    -0.65
    clinton
    -0.63
    umerable
    -0.61
    eem
    -0.60
     concess
    -0.59
     Dayton
    -0.59
    issan
    -0.59
     partName
    -0.58
    OPLE
    -0.58
    POSITIVE LOGITS
    sta
    1.48
    sters
    1.47
    ster
    1.46
    bang
    1.38
    rene
    1.20
    busters
    1.18
    buster
    1.09
    masters
    1.02
    members
    0.97
    leader
    0.96
    Activations Density 0.045%

    No Known Activations