© 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. 4776
    Prev
    Next
    INDEX
    Explanations

    words related to illicit behavior or controversial topics

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "asymmetry" or related concepts

    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
     herald
    -0.72
     file
    -0.69
     teams
    -0.68
     Colts
    -0.67
     guardian
    -0.66
     commencement
    -0.65
     pillars
    -0.64
     fin
    -0.63
     RB
    -0.63
     reg
    -0.63
    POSITIVE LOGITS
    asy
    4.59
    ASY
    1.43
    aky
    1.20
    ased
    1.06
    ase
    1.04
    asia
    1.04
    acy
    1.03
    asty
    1.01
    assy
    1.01
    antis
    1.00
    Activations Density 0.016%

    No Known Activations