© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 10-RES-JB
    11. 7113
    Prev
    Next
    INDEX
    Explanations

    references to specific companies

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns related to companies and telecommunications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    genre
    -0.78
    dyl
    -0.73
    indu
    -0.66
    udeb
    -0.65
    leans
    -0.64
    inges
    -0.63
    include
    -0.62
    irlf
    -0.62
    ibliography
    -0.61
    absor
    -0.60
    POSITIVE LOGITS
     Holdings
    1.25
     Corp
    1.24
     Corporation
    1.21
     Ltd
    1.12
     subsidiary
    1.07
     Technologies
    1.06
     Inc
    1.02
     Networks
    1.01
     Industries
    1.00
     Mobility
    1.00
    Activations Density 0.213%

    No Known Activations