© 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. 0-RES-JB
    11. 8189
    Prev
    Next
    INDEX
    Explanations

    SQL injection terms related to cybersecurity

    oai_token-act-pair · gpt-3.5-turbo

    references to cyber security threats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ourses
    -0.74
    uberty
    -0.70
    Neill
    -0.68
    urable
    -0.66
    tnc
    -0.65
    20439
    -0.64
    olon
    -0.63
    iggurat
    -0.63
    aban
    -0.63
    ãĥ¯ãĥ³
    -0.63
    POSITIVE LOGITS
     Avenger
    0.66
     alias
    0.65
    els
    0.64
    ature
    0.63
    imately
    0.62
    assed
    0.62
    alias
    0.62
     gloves
    0.62
    footed
    0.59
     brushes
    0.58
    Activations Density 0.000%

    No Known Activations