© 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. 19705
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to the name "Elijah"

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals and specific place references

    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
    SourceFile
    -0.74
    unity
    -0.73
    nant
    -0.69
    henko
    -0.68
    sych
    -0.66
     HG
    -0.66
     IMAGES
    -0.66
     Tanaka
    -0.65
     Imaging
    -0.65
     Gott
    -0.64
    POSITIVE LOGITS
    ijah
    1.07
    ives
    0.97
    mere
    0.81
    inav
    0.81
    iving
    0.80
    iver
    0.79
    isions
    0.77
    ived
    0.76
    ords
    0.75
    earchers
    0.73
    Activations Density 0.018%

    No Known Activations