Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 6821
    Prev
    Next
    INDEX
    Explanations

    references to concentration camps, forced labor, and similar historical atrocities

    oai_token-act-pair · gpt-3.5-turbo

    references to historical atrocities and oppressive conditions, particularly related to concentration camps and forced labor

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wcsstore
    -0.87
     Toast
    -0.84
     Prediction
    -0.74
    natureconservancy
    -0.73
     Cary
    -0.72
     Investors
    -0.69
    Shares
    -0.68
     Prosper
    -0.66
    VP
    -0.65
     Drivers
    -0.64
    POSITIVE LOGITS
     Auschwitz
    1.20
     inmates
    1.16
    chwitz
    1.15
     detainees
    1.06
     confinement
    0.99
     inmate
    0.96
     prisoners
    0.95
     barracks
    0.95
     dehuman
    0.91
     gul
    0.90
    Activations Density 0.117%

    No Known Activations