© 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. 10-RES-JB
    11. 857
    Prev
    Next
    INDEX
    Explanations

    phrases related to prisons, prisoners, and prisoner treatment

    oai_token-act-pair · gpt-3.5-turbo

    references to prisoners and related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    drive
    -0.77
    ijn
    -0.66
    xi
    -0.66
    ilde
    -0.65
    lag
    -0.64
     Ples
    -0.64
    ãĤ¤ãĥĪ
    -0.63
    dust
    -0.62
    orie
    -0.62
    ilion
    -0.62
    POSITIVE LOGITS
     incarcerated
    1.07
     inmates
    0.98
     sentenced
    0.96
     prisoners
    0.92
     inmate
    0.88
     detainees
    0.83
     housed
    0.83
     prisoner
    0.82
     jailed
    0.81
    icts
    0.79
    Activations Density 0.065%

    No Known Activations