© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 9946
    Prev
    Next
    INDEX
    Explanations

    technical terms related to software or system vulnerabilities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to security vulnerabilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ctory
    -0.77
    minist
    -0.75
    rones
    -0.71
     funer
    -0.68
     farewell
    -0.67
    ollo
    -0.67
    amaz
    -0.66
     funeral
    -0.65
     adject
    -0.65
     FANTASY
    -0.65
    POSITIVE LOGITS
    CVE
    1.30
     CVE
    1.30
    ulnerability
    1.12
     exploited
    1.05
     affecting
    1.01
     vulnerability
    1.00
     plag
    1.00
     flaw
    0.95
     exploit
    0.94
     vulnerabilities
    0.92
    Activations Density 0.181%

    No Known Activations