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. 8267
    Prev
    Next
    INDEX
    Explanations

    references to the use of torture in contexts related to terrorism and intelligence activities

    oai_token-act-pair · gpt-3.5-turbo

    references to torture and its implications within intelligence agencies

    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
     Pony
    -0.98
    coins
    -0.94
    MpServer
    -0.89
     cryptoc
    -0.87
     Volkswagen
    -0.85
     Porsche
    -0.82
     wallets
    -0.82
     âĹ
    -0.81
    Bitcoin
    -0.81
    Market
    -0.80
    POSITIVE LOGITS
     detainee
    1.97
     Guant
    1.97
     detainees
    1.89
     Guantanamo
    1.87
     interrog
    1.61
     interrogation
    1.59
     torture
    1.53
     detention
    1.47
     Detention
    1.39
     CIA
    1.38
    Activations Density 0.247%

    No Known Activations