© 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. 4-RES-JB
    11. 4565
    Prev
    Next
    INDEX
    Explanations

    references to leaks or information breaches

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "leak."

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

    No Comments

    Negative Logits
     DRAG
    -0.74
    ŃĶ
    -0.71
    ctrl
    -0.69
     endeavour
    -0.66
     Bravo
    -0.60
     Rooney
    -0.60
     Patri
    -0.60
     Kenobi
    -0.60
    TYPE
    -0.59
    Goal
    -0.58
    POSITIVE LOGITS
    doms
    0.81
    nesses
    0.78
    ileaks
    0.74
    oing
    0.73
    opian
    0.73
    overs
    0.72
    arding
    0.72
    ibility
    0.71
    assic
    0.70
    eton
    0.69
    Activations Density 0.032%

    No Known Activations