© 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. 18260
    Prev
    Next
    INDEX
    Explanations

    words related to business operations and models

    oai_token-act-pair · gpt-3.5-turbo

    references to business models and business-related 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
    gger
    -0.73
    ãĥŃ
    -0.66
     Primal
    -0.63
    ifer
    -0.62
    ados
    -0.61
     UW
    -0.61
     EW
    -0.60
    arity
    -0.60
    ody
    -0.59
     LW
    -0.57
    POSITIVE LOGITS
     dealings
    1.02
     ventures
    0.96
    INESS
    0.95
    woman
    0.92
     enterprises
    0.88
     mogul
    0.86
    people
    0.85
     owners
    0.84
     interests
    0.84
    Desk
    0.83
    Activations Density 0.048%

    No Known Activations