© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    11. 22470
    Prev
    Next
    INDEX
    Explanations

    body parts that have been physically attacked or injured

    oai_token-act-pair · gpt-3.5-turbo

    references to injuries and body parts related to violence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DragonMagazine
    -0.95
    soDeliveryDate
    -0.87
    quickShipAvailable
    -0.83
    inventoryQuantity
    -0.83
    arcity
    -0.80
     Tycoon
    -0.76
    wcsstore
    -0.76
    iesta
    -0.71
    sbm
    -0.70
    MQ
    -0.70
    POSITIVE LOGITS
    bone
    1.22
     cavity
    1.17
    bones
    1.01
     bone
    0.98
     lobe
    0.97
     bones
    0.94
     artery
    0.86
     throat
    0.86
     verte
    0.86
     cheeks
    0.85
    Activations Density 0.121%

    No Known Activations