© 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. 8-RES-JB
    11. 1298
    Prev
    Next
    INDEX
    Explanations

    phrases related to companies and legal entities

    oai_token-act-pair · gpt-3.5-turbo

    the presence of limited liability company (LLC) references in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bolt
    -0.79
    grain
    -0.78
    lite
    -0.75
    \":
    -0.75
    fulness
    -0.75
    cone
    -0.70
    faced
    -0.68
    liner
    -0.68
    cho
    -0.68
    liest
    -0.65
    POSITIVE LOGITS
    orporated
    1.19
    iffe
    1.01
    orpor
    0.91
    rador
    0.88
    redited
    0.84
    ateral
    0.83
    ittle
    0.82
     incorpor
    0.81
    endiary
    0.80
     Ltd
    0.80
    Activations Density 0.044%

    No Known Activations