© 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 EvalsExportsinterp-engineNEWAPI 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. 12-RES-JB
    11. 4532
    Prev
    Next
    INDEX
    Explanations

    phrases related to technology features, cybersecurity, and privacy protection

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to security vulnerabilities and threats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ellen
    -0.84
    áµ
    -0.82
    ynes
    -0.81
    200000
    -0.78
    HCR
    -0.77
    emin
    -0.77
    ONSORED
    -0.76
    ulously
    -0.75
    ocamp
    -0.75
    icz
    -0.74
    POSITIVE LOGITS
     malware
    1.48
     ransomware
    1.41
     viruses
    1.30
     malicious
    1.25
     hacks
    1.24
     hackers
    1.24
     tampering
    1.23
     unauthorized
    1.21
     spoof
    1.20
     exploits
    1.18
    Activations Density 0.290%

    No Known Activations