© 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. 17276
    Prev
    Next
    INDEX
    Explanations

    terms related to cyber attacks and technical tactics

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "trojan" in various contexts

    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
    ulse
    -0.75
    maxwell
    -0.74
    rentices
    -0.73
    ukong
    -0.69
    ++++++++++++++++
    -0.69
    hips
    -0.68
    rator
    -0.67
     Bradford
    -0.65
    ģ«
    -0.63
    rison
    -0.63
    POSITIVE LOGITS
     tro
    1.29
    dden
    1.05
    tted
    1.00
    tsky
    0.94
    tro
    0.93
    oping
    0.87
    opard
    0.86
    toe
    0.84
    isure
    0.81
    culosis
    0.76
    Activations Density 0.011%

    No Known Activations