© 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. 6-RES-JB
    11. 7858
    Prev
    Next
    INDEX
    Explanations

    specific dates written in the format day/month

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the number '4'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vier
    -0.72
     Whitman
    -0.72
    esville
    -0.68
    venue
    -0.68
     Cheong
    -0.66
     Vaugh
    -0.66
    iday
    -0.64
     Winchester
    -0.63
     woo
    -0.63
    becca
    -0.62
    POSITIVE LOGITS
    teenth
    1.37
    teen
    1.34
    eva
    1.01
    hyde
    0.93
    some
    0.91
    cyl
    0.85
    square
    0.85
    Chan
    0.83
    66666666
    0.82
    th
    0.82
    Activations Density 0.124%

    No Known Activations