© 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. 2-RES-JB
    11. 15676
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly related to companies or organizations

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns that refer to corporations or companies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĻĤ
    -0.84
     sheet
    -0.69
    ormal
    -0.69
    jad
    -0.68
    itability
    -0.68
    ises
    -0.67
    incarn
    -0.67
    Äĩ
    -0.67
    adal
    -0.66
    ests
    -0.65
    POSITIVE LOGITS
     Ltd
    1.38
     Industries
    1.26
     Corp
    1.21
     Inc
    1.19
     Corporation
    1.19
     Enterprises
    1.16
     Laboratories
    1.15
     Technologies
    1.15
     Solutions
    1.15
     Associates
    1.12
    Activations Density 0.056%

    No Known Activations