© 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. 12-RES-JB
    11. 4692
    Prev
    Next
    INDEX
    Explanations

    mentions of business-related topics like revenue, financial goals, and company performance

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    financial metrics and performance indicators related to company revenue and growth

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
     Maine
    -0.73
     negro
    -0.70
     pacif
    -0.70
     homophobia
    -0.70
     wilderness
    -0.69
     outlawed
    -0.69
     murder
    -0.69
     warp
    -0.69
     poisonous
    -0.68
     invaders
    -0.67
    POSITIVE LOGITS
     Investors
    1.34
     Investor
    1.30
    Companies
    1.27
    Company
    1.27
    CEO
    1.27
    DAQ
    1.25
    NYSE
    1.21
     IPO
    1.20
     investor
    1.17
     investors
    1.16
    Activations Density 1.083%

    No Known Activations