© 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. 4818
    Prev
    Next
    INDEX
    Explanations

    words related to the entity "Lin"

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of the word "Metroline" in various contexts

    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
     Seym
    -0.87
    awei
    -0.86
    ModLoader
    -0.78
    ģĸ
    -0.74
    rahim
    -0.73
    ansas
    -0.73
    ADRA
    -0.73
    avorite
    -0.72
    catentry
    -0.69
    EStream
    -0.67
    POSITIVE LOGITS
    ergic
    1.09
    eman
    0.99
     Rouge
    0.90
    strument
    0.88
    ium
    0.87
    burg
    0.85
    fo
    0.82
    hurst
    0.82
    ights
    0.81
    quist
    0.80
    Activations Density 0.013%

    No Known Activations