© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 22516
    Prev
    Next
    INDEX
    Explanations

    mentions or descriptions of different types of camps, such as internment camps or military camps

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of camps

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nce
    -0.75
    Journal
    -0.67
    WN
    -0.67
    rious
    -0.66
     magnification
    -0.63
    thy
    -0.60
     Universe
    -0.60
    theless
    -0.60
    Month
    -0.59
    Republic
    -0.58
    POSITIVE LOGITS
     camps
    1.19
    camp
    1.14
    ites
    1.04
    ite
    1.03
    ovie
    0.92
     camp
    0.92
    fires
    0.89
    chool
    0.83
     tents
    0.83
     Camp
    0.83
    Activations Density 0.010%

    No Known Activations