© 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. 8538
    Prev
    Next
    INDEX
    Explanations

    terms related to crimes and violations against humanity

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to crimes and human rights violations

    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
    soDeliveryDate
    -0.97
    éĹĺ
    -0.81
    DragonMagazine
    -0.80
    uyomi
    -0.78
    zl
    -0.78
    ETF
    -0.77
    swick
    -0.76
    çīĪ
    -0.75
    hower
    -0.75
    }}}
    -0.75
    POSITIVE LOGITS
     civilians
    1.06
     innocent
    0.97
     humanity
    0.89
     whom
    0.84
     Humanity
    0.84
     him
    0.82
     unborn
    0.80
     targets
    0.78
     women
    0.77
     gays
    0.75
    Activations Density 0.055%

    No Known Activations