© 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. 9-RES-JB
    11. 4246
    Prev
    Next
    INDEX
    Explanations

    words related to creating chaos or causing harm

    oai_token-act-pair · gpt-3.5-turbo

    terms related to destruction or chaos

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    antz
    -0.73
    croft
    -0.72
    cius
    -0.71
     Quartz
    -0.69
    missive
    -0.67
     Collider
    -0.66
    oglobin
    -0.65
    soDeliveryDate
    -0.65
     Boards
    -0.64
    chrom
    -0.64
    POSITIVE LOGITS
     havoc
    1.54
     damage
    1.01
     wre
    0.88
     mayhem
    0.88
     carnage
    0.87
     devastation
    0.86
    damage
    0.81
     inflicted
    0.81
     blows
    0.80
     wonders
    0.78
    Activations Density 0.076%

    No Known Activations