© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 5300
    Prev
    Next
    INDEX
    Explanations

    words containing the substring "cons"

    oai_token-act-pair · gpt-3.5-turbo

    references to "cons" or related terms that discuss conditions or situations involving the concept of conservatism

    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
     Norn
    -0.70
     blasted
    -0.67
     Gy
    -0.66
     Doodle
    -0.66
     mud
    -0.65
     sued
    -0.64
     clay
    -0.62
     Misty
    -0.62
     shy
    -0.62
     bash
    -0.62
    POSITIVE LOGITS
    cons
    4.14
    Cons
    2.34
     Cons
    1.75
    con
    1.72
     CONS
    1.40
     cons
    1.36
    CON
    1.25
    comm
    1.17
    conserv
    1.17
    pres
    1.03
    Activations Density 0.011%

    No Known Activations