© 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. 6-RES-JB
    11. 9676
    Prev
    Next
    INDEX
    Explanations

    statements or quotes within a text

    oai_token-act-pair · gpt-3.5-turbo

    instances of numerical ratings or scores associated with evaluations

    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
     bear
    -0.70
     instit
    -0.66
     trades
    -0.64
     Jinping
    -0.64
     citiz
    -0.63
     retreat
    -0.62
     dilig
    -0.62
     lifes
    -0.62
     diseng
    -0.62
     goods
    -0.61
    POSITIVE LOGITS
    Unlike
    0.98
    Instead
    0.98
    Both
    0.97
    ccording
    0.96
    Specifically
    0.95
    Asked
    0.94
    Earlier
    0.94
    Although
    0.93
    Though
    0.92
    They
    0.91
    Activations Density 0.431%

    No Known Activations