© 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 EvalsExportsAPI 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. 0-RES-JB
    11. 10029
    Prev
    Next
    INDEX
    Explanations

    words related to institutional aspects or institutions

    oai_token-act-pair · gpt-3.5-turbo

    references to institutional frameworks or systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Scroll
    -0.75
    ry
    -0.73
    oute
    -0.72
     Nib
    -0.70
     Droid
    -0.69
    ries
    -0.69
     timer
    -0.68
    ttes
    -0.68
     rays
    -0.68
     Lines
    -0.68
    POSITIVE LOGITS
     institutional
    3.60
    itutional
    2.33
     institutions
    1.76
     institution
    1.63
     systemic
    1.47
     Instit
    1.39
     organizational
    1.30
     societal
    1.24
     endemic
    1.20
     governmental
    1.20
    Activations Density 0.014%

    No Known Activations