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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 11475
    Prev
    Next
    INDEX
    Explanations

    descriptions of physical restraint or confinement methods

    oai_token-act-pair · gpt-3.5-turbo

    descriptions of abusive or torturous situations and practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ahime
    -0.91
     Entreprene
    -0.84
     congr
    -0.78
    sonian
    -0.78
    inventoryQuantity
    -0.76
     Reply
    -0.75
     Etsy
    -0.75
     Inher
    -0.73
    assetsadobe
    -0.73
     Millenn
    -0.72
    POSITIVE LOGITS
     torture
    1.53
     interrog
    1.35
     tortured
    1.35
     shack
    1.34
     interrogation
    1.30
     detainees
    1.29
     interrogated
    1.28
     handcuffed
    1.27
     chained
    1.25
     inmates
    1.21
    Activations Density 0.477%

    No Known Activations