© 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. 0-RES-JB
    11. 1972
    Prev
    Next
    INDEX
    Explanations

    proper nouns indicating business partnerships or entities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of corporate or organizational partnerships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     arbitrary
    -0.82
     grain
    -0.74
    loading
    -0.72
    ðĿ
    -0.68
     baff
    -0.67
     erase
    -0.66
     arbitrarily
    -0.65
     ho
    -0.65
     disturb
    -0.64
    handle
    -0.64
    POSITIVE LOGITS
     Partners
    3.81
     Partner
    2.11
     partners
    1.82
     Associates
    1.74
     Partnership
    1.69
     partnerships
    1.66
     partner
    1.48
     Ventures
    1.45
     Investments
    1.33
     partnership
    1.33
    Activations Density 0.010%

    No Known Activations