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

    Neuronpedia

    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. 3600
    Prev
    Next
    INDEX
    Explanations

    phrases describing violent actions or events

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating violence or attacks

    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
    -0.83
    ItemThumbnailImage
    -0.71
    SourceFile
    -0.70
    inventoryQuantity
    -0.69
    tions
    -0.69
    BuyableInstoreAndOnline
    -0.68
    swick
    -0.67
    paren
    -0.67
    aird
    -0.66
     PsyNet
    -0.66
    POSITIVE LOGITS
     unsuspecting
    1.17
    erous
    0.96
     behalf
    0.84
     unarmed
    0.79
     hordes
    0.78
    astically
    0.78
     subordinates
    0.77
     indiscrim
    0.76
     unwitting
    0.76
     anyone
    0.76
    Activations Density 0.210%

    No Known Activations