© 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. 6-RES-JB
    11. 13535
    Prev
    Next
    INDEX
    Explanations

    words related to cyber technology and security

    oai_token-act-pair · gpt-3.5-turbo

    references to cyber-related topics and terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Clement
    -0.80
     LINE
    -0.73
     Jinn
    -0.72
    ++++++++++++++++
    -0.71
    ered
    -0.70
    IELD
    -0.70
     Flav
    -0.69
     Pearce
    -0.69
    UCT
    -0.68
     Chamberlain
    -0.67
    POSITIVE LOGITS
    netic
    1.48
    punk
    1.23
    attacks
    1.03
    crime
    0.96
    security
    0.92
    activ
    0.90
    threat
    0.90
    assault
    0.89
    bull
    0.88
    attack
    0.86
    Activations Density 0.021%

    No Known Activations