© 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. 3390
    Prev
    Next
    INDEX
    Explanations

    mentions of cyber threats or malware

    oai_token-act-pair · gpt-3.5-turbo

    words related to severe conditions or risks, particularly in the context of health and safety

    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
     :=
    -0.66
     immedi
    -0.66
     clarity
    -0.61
     emphas
    -0.59
    amaz
    -0.58
     Defin
    -0.56
     caut
    -0.55
     Airl
    -0.55
     till
    -0.54
     endeavour
    -0.53
    POSITIVE LOGITS
     plagiar
    0.98
     hoax
    0.88
     secretly
    0.87
     pedoph
    0.87
     illegally
    0.85
     faked
    0.84
     actually
    0.80
     improperly
    0.79
     fraud
    0.77
     inappropriately
    0.77
    Activations Density 0.792%

    No Known Activations