© 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. 6283
    Prev
    Next
    INDEX
    Explanations

    associations related to organizations and industries

    oai_token-act-pair · gpt-3.5-turbo

    references to various trade associations

    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
    inventoryQuantity
    -0.85
    flows
    -0.75
     drums
    -0.74
     vocals
    -0.71
    zac
    -0.70
     balloons
    -0.68
    imens
    -0.68
     wells
    -0.67
    etheus
    -0.65
     bunk
    -0.65
    POSITIVE LOGITS
     Association
    2.20
     Associ
    1.91
     Federation
    1.60
     Society
    1.54
     Owners
    1.50
     Confederation
    1.40
     Improvement
    1.38
     Council
    1.35
     Organization
    1.35
     Manufact
    1.35
    Activations Density 0.280%

    No Known Activations