© 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. 6-RES-JB
    11. 14587
    Prev
    Next
    INDEX
    Explanations

    words related to hacking and software security

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Hack."

    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
    ãħĭ
    -0.76
     occas
    -0.75
     concess
    -0.72
     rul
    -0.67
     conflic
    -0.63
     patronage
    -0.62
     compr
    -0.60
    iatrics
    -0.60
    åĬ
    -0.60
    reply
    -0.60
    POSITIVE LOGITS
    intosh
    1.41
    athon
    1.29
    aday
    1.16
    enberg
    1.05
    driver
    0.97
    busters
    0.90
    Hack
    0.89
    ett
    0.88
    nik
    0.88
    ademic
    0.87
    Activations Density 0.037%

    No Known Activations