© 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. 4-RES-JB
    11. 6884
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to companies, organizations, and brand names

    oai_token-act-pair · gpt-3.5-turbo

    references to specific brands or franchises

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

    No Comments

    Negative Logits
    vari
    -0.67
     Kenyan
    -0.62
     kindred
    -0.61
     opposing
    -0.60
    wid
    -0.59
    inn
    -0.58
     Lovely
    -0.58
    selection
    -0.58
     Adin
    -0.58
    tackle
    -0.57
    POSITIVE LOGITS
     Fridays
    0.76
    atoes
    0.76
    Course
    0.72
     Arcade
    0.71
    ffen
    0.70
     Channel
    0.67
     Express
    0.65
     ®
    0.65
     Revival
    0.65
    Render
    0.64
    Activations Density 0.152%

    No Known Activations