© 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. 7-RES-JB
    11. 12440
    Prev
    Next
    INDEX
    Explanations

    phrases related to being imprisoned or held captive

    oai_token-act-pair · gpt-3.5-turbo

    references to prisoners of war

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Boll
    -0.78
    orp
    -0.73
    OPA
    -0.71
     Remastered
    -0.71
    orie
    -0.68
    lag
    -0.67
     Ples
    -0.65
    wig
    -0.65
    amera
    -0.64
     Blizz
    -0.64
    POSITIVE LOGITS
     prisoners
    1.01
     prisoner
    0.89
     inmates
    0.89
     captives
    0.89
     sentenced
    0.87
     detainees
    0.81
     incarcerated
    0.80
    prison
    0.78
     jailed
    0.76
     inmate
    0.76
    Activations Density 0.032%

    No Known Activations