© 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. 11-RES-JB
    11. 20813
    Prev
    Next
    INDEX
    Explanations

    terminology related to law enforcement and security

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to security and risk assessment

    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
     princ
    -0.73
     Everywhere
    -0.71
    thood
    -0.64
     coffin
    -0.64
    ruary
    -0.64
     everywhere
    -0.64
     unanimous
    -0.64
     congratulated
    -0.63
     Bliss
    -0.62
     ecstatic
    -0.60
    POSITIVE LOGITS
     pose
    0.97
     endanger
    0.96
     inappropriately
    0.92
     adversely
    0.92
     reasonably
    0.89
     otherwise
    0.88
     harm
    0.86
     posed
    0.86
     jeopard
    0.85
     potentially
    0.84
    Activations Density 0.361%

    No Known Activations