© 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 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. 20825
    Prev
    Next
    INDEX
    Explanations

    phrases related to harsh physical treatment or conditions

    oai_token-act-pair · gpt-3.5-turbo

    references to torture and inhumane treatment in a prison or military context

    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
    soType
    -0.92
    natureconservancy
    -0.88
    Shares
    -0.83
     Prediction
    -0.81
     Catalyst
    -0.81
    wcsstore
    -0.81
     jQuery
    -0.77
    Bloomberg
    -0.77
    nect
    -0.77
     Shares
    -0.76
    POSITIVE LOGITS
     detainees
    1.39
     torture
    1.36
     prisoners
    1.31
     prisons
    1.26
     inmates
    1.23
     prisoner
    1.22
     interrogation
    1.22
     detainee
    1.18
     detention
    1.18
     confinement
    1.17
    Activations Density 0.723%

    No Known Activations