© 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. 12-RES-JB
    11. 2995
    Prev
    Next
    INDEX
    Explanations

    words related to actions such as 'promulgating', 'exhuming', 'dispensing', 'reconfiguring', 'attaching', 'rebadging', 'recommitting', and 'rectifying'

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    words related to regulations and legal processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
     behavi
    -0.78
    NESS
    -0.71
     handling
    -0.70
     successors
    -0.70
     advancement
    -0.70
     wounding
    -0.69
     immersion
    -0.68
     stability
    -0.68
     settling
    -0.67
     empowerment
    -0.67
    POSITIVE LOGITS
    cribed
    1.29
    idated
    1.24
    oned
    1.24
    illed
    1.24
    lated
    1.23
    itted
    1.23
    idden
    1.22
    rozen
    1.22
    ifled
    1.22
    opted
    1.21
    Activations Density 0.357%

    No Known Activations