© 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. 16073
    Prev
    Next
    INDEX
    Explanations

    organizations and companies

    oai_token-act-pair · gpt-3.5-turbo

    mentions of funding sources or financial relationships related to political action or causes

    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
    estyles
    -0.70
    ilege
    -0.67
    ocious
    -0.67
     slee
    -0.66
     wrinkles
    -0.64
     madness
    -0.61
     breeze
    -0.61
     anx
    -0.60
    reci
    -0.59
     cliff
    -0.59
    POSITIVE LOGITS
     organisations
    1.25
     corporations
    1.21
     nonprofit
    1.20
     organizations
    1.20
     entities
    1.19
     subsidiaries
    1.18
     nonprofits
    1.18
     corporation
    1.15
     companies
    1.09
    Companies
    1.07
    Activations Density 1.304%

    No Known Activations