© 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. 11-RES-JB
    11. 22664
    Prev
    Next
    INDEX
    Explanations

    discussions related to internet security

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to security and technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
    oaded
    -0.77
    orie
    -0.76
    sonian
    -0.74
     ferment
    -0.74
     Rachel
    -0.73
     Frankie
    -0.73
     Staten
    -0.72
    eteenth
    -0.72
    interstitial
    -0.71
    ëĭ
    -0.71
    POSITIVE LOGITS
     cybersecurity
    1.99
     security
    1.86
    Security
    1.83
     encryption
    1.76
    security
    1.71
     Security
    1.69
     cryptography
    1.67
     vulnerabilities
    1.67
     malware
    1.64
     encrypt
    1.62
    Activations Density 0.643%

    No Known Activations