© 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. 10-RES-JB
    11. 12448
    Prev
    Next
    INDEX
    Explanations

    security-related terms and phrases

    oai_token-act-pair · gpt-3.5-turbo

    terms related to security and protective measures

    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
    bender
    -0.73
    irez
    -0.68
    hler
    -0.68
    fred
    -0.65
    annis
    -0.65
    udi
    -0.63
    swick
    -0.63
    iste
    -0.62
    slow
    -0.62
    mot
    -0.62
    POSITIVE LOGITS
     perimeter
    0.93
     passwords
    0.88
     cryptographic
    0.87
     enclave
    0.83
     communications
    0.83
    rets
    0.79
     access
    0.75
     communication
    0.75
     deposit
    0.74
     cryptography
    0.74
    Activations Density 0.033%

    No Known Activations