© 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. 6-RES-JB
    11. 8520
    Prev
    Next
    INDEX
    Explanations

    phrases related to excessive force or torture

    oai_token-act-pair · gpt-3.5-turbo

    terms related to instances of excessive use of force and torture

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soType
    -0.79
    idges
    -0.74
    ellar
    -0.73
    alg
    -0.73
    aline
    -0.71
     Balance
    -0.70
    sonian
    -0.69
     calculator
    -0.69
     theorem
    -0.69
    isSpecialOrderable
    -0.68
    POSITIVE LOGITS
     dehuman
    1.09
     brutality
    1.08
     torture
    1.08
     abuses
    1.00
     punishments
    0.96
     detainees
    0.93
     killings
    0.93
     inflicted
    0.93
     unarmed
    0.92
     inhuman
    0.91
    Activations Density 0.362%

    No Known Activations