© 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. 9-RES-JB
    11. 1904
    Prev
    Next
    INDEX
    Explanations

    phrases related to causing harm, damage, and negative consequences

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to harm and damage

    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
    */(
    -0.73
    IQ
    -0.72
    quire
    -0.71
    natureconservancy
    -0.69
    lio
    -0.68
    dayName
    -0.67
    oS
    -0.67
    FN
    -0.66
    soDeliveryDate
    -0.66
    ophy
    -0.65
    POSITIVE LOGITS
     inflicted
    1.55
     casualties
    1.08
     wounds
    1.07
     suffered
    1.07
     griev
    1.07
     incurred
    1.06
     injuries
    1.03
     loss
    1.01
     wounding
    0.99
     damages
    0.99
    Activations Density 0.675%

    No Known Activations