© 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. 0-RES-JB
    11. 7811
    Prev
    Next
    INDEX
    Explanations

    Common Vulnerabilities and Exposures (CVE) identifiers

    oai_token-act-pair · gpt-3.5-turbo

    references to CVE identifiers and associated security terms

    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
     Patron
    -0.74
    HUD
    -0.64
    cation
    -0.63
    ience
    -0.63
    Ëľ
    -0.63
     Morrison
    -0.63
    Pod
    -0.62
    Dom
    -0.62
    vironment
    -0.62
     contraction
    -0.62
    POSITIVE LOGITS
     NCT
    2.75
     CVE
    2.62
     SHA
    2.14
    CVE
    2.11
    SHA
    1.72
    sha
    1.50
     centrif
    1.50
    ventional
    1.33
    doi
    1.00
     CRC
    1.00
    Activations Density 0.062%

    No Known Activations