© 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. 9-RES-JB
    11. 11230
    Prev
    Next
    INDEX
    Explanations

    terms related to law, organization, and authority

    oai_token-act-pair · gpt-3.5-turbo

    references to roles and responsibilities in various professional contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     cryptocurrencies
    -0.80
     stances
    -0.75
     triangles
    -0.74
     powd
    -0.73
     skulls
    -0.72
     visas
    -0.72
     currencies
    -0.72
    bows
    -0.72
     patents
    -0.71
     surgeries
    -0.71
    POSITIVE LOGITS
     careg
    1.38
     administrator
    1.33
     performer
    1.32
     abuser
    1.31
     servant
    1.30
     lover
    1.30
     operator
    1.30
     educator
    1.28
     supervisor
    1.28
    operator
    1.27
    Activations Density 0.526%

    No Known Activations