© 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. 3-RES-JB
    11. 23688
    Prev
    Next
    INDEX
    Explanations

    terms related to hacking or being hacked

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "hack."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Debor
    -0.85
    psons
    -0.75
    itia
    -0.72
     Niet
    -0.70
     livest
    -0.69
    eda
    -0.68
    zo
    -0.68
     Mai
    -0.67
    quart
    -0.66
    cci
    -0.66
    POSITIVE LOGITS
    acked
    1.05
    intosh
    0.87
    ACK
    0.86
    acks
    0.85
    enzie
    0.82
    acker
    0.77
    luster
    0.77
    lash
    0.73
    acking
    0.72
    innon
    0.71
    Activations Density 0.014%

    No Known Activations