© 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. 0-RES-JB
    11. 2456
    Prev
    Next
    INDEX
    Explanations

    references to prisoners and imprisonment

    oai_token-act-pair · gpt-3.5-turbo

    references to prisoners

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ï¸ı
    -0.77
    luence
    -0.76
    eor
    -0.72
    EMA
    -0.69
     Etsy
    -0.68
    Sty
    -0.68
    osity
    -0.67
    opic
    -0.67
    heast
    -0.66
    ocity
    -0.65
    POSITIVE LOGITS
     prisoners
    3.73
     prisoner
    3.13
     inmates
    2.65
     detainees
    2.52
     captives
    2.42
     Prison
    2.31
    prison
    2.21
     prisons
    2.13
     hostages
    2.07
     inmate
    2.02
    Activations Density 0.020%

    No Known Activations