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. 8608
    Prev
    Next
    INDEX
    Explanations

    references to imprisonment, torture, and confinement

    oai_token-act-pair · gpt-3.5-turbo

    references to human rights violations and the conditions of detention camps

    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
    soDeliveryDate
    -0.76
     RC
    -0.74
    wcsstore
    -0.74
     Prediction
    -0.69
     EF
    -0.68
    Roll
    -0.66
     Supplement
    -0.64
     WS
    -0.64
     Meteor
    -0.64
    âĤ¬
    -0.63
    POSITIVE LOGITS
     detainees
    1.06
    chwitz
    1.03
     confinement
    1.03
     inmates
    1.03
    anamo
    1.02
     Guantanamo
    1.02
     torture
    1.01
     Auschwitz
    0.99
     prisoners
    0.97
    atorium
    0.95
    Activations Density 0.169%

    No Known Activations