© 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. 8-RES-JB
    11. 12253
    Prev
    Next
    INDEX
    Explanations

    statements that are negated or contradicted

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating denial or the concept of "not being."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    egu
    -0.91
     understandably
    -0.83
    erity
    -0.81
    severe
    -0.75
     assurances
    -0.74
     cautiously
    -0.74
     patiently
    -0.73
    iscal
    -0.72
     sorely
    -0.71
    oso
    -0.70
    POSITIVE LOGITS
     exist
    0.92
     anymore
    0.88
     existed
    0.85
     english
    0.79
     exists
    0.75
     fucking
    0.73
     shit
    0.70
     anything
    0.70
     genders
    0.69
     lol
    0.69
    Activations Density 0.752%

    No Known Activations