© 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. 11-RES-JB
    11. 5669
    Prev
    Next
    INDEX
    Explanations

    phrases related to corporate entities and ownership

    oai_token-act-pair · gpt-3.5-turbo

    corporate structures and relationships between companies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hars
    -0.74
    lash
    -0.73
    thirst
    -0.72
     ultras
    -0.72
     jams
    -0.71
     fuss
    -0.71
    aptic
    -0.71
    scar
    -0.69
     applause
    -0.69
     trash
    -0.68
    POSITIVE LOGITS
     subsidiaries
    1.84
     subsidiary
    1.61
     incorpor
    1.50
     LLC
    1.40
     shareholders
    1.34
     trustee
    1.32
     shareholder
    1.29
     corporation
    1.26
     Holdings
    1.26
     affiliates
    1.25
    Activations Density 0.450%

    No Known Activations