© 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. 9-RES-JB
    11. 15935
    Prev
    Next
    INDEX
    Explanations

    phrases containing the prefix "ex-" with negative connotations

    oai_token-act-pair · gpt-3.5-turbo

    references to past relationships or former partners

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the dash following words beginning with "ex"

    Explanation Uploaded by User
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uden
    -0.82
     shading
    -0.80
     dances
    -0.76
     Zup
    -0.74
     underlying
    -0.72
     weighted
    -0.71
     dashed
    -0.68
     amplification
    -0.68
     amounts
    -0.67
     largeDownload
    -0.67
    POSITIVE LOGITS
    girlfriend
    1.53
    husband
    1.39
    employ
    1.37
    wife
    1.29
    members
    1.25
    military
    1.24
    member
    1.22
    president
    1.21
    Soviet
    1.20
    sold
    1.16
    Activations Density 0.024%

    No Known Activations