© 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. 6951
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific individuals or names

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Reagan."

    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
    upon
    -0.77
    İĭ
    -0.76
    hovah
    -0.68
     Peg
    -0.67
     abdom
    -0.66
    bred
    -0.65
    lihood
    -0.63
     bour
    -0.61
     breed
    -0.61
    ĵĺ
    -0.61
    POSITIVE LOGITS
    igans
    1.04
    za
    0.96
    azi
    0.93
    zeb
    0.92
    furt
    0.92
    ajor
    0.91
    igan
    0.89
    agan
    0.89
    ja
    0.88
    arde
    0.88
    Activations Density 0.008%

    No Known Activations