© 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 EvalsExportsinterp-engineNEWAPI 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. 8-RES-JB
    11. 12420
    Prev
    Next
    INDEX
    Explanations

    phrases related to progression, development, and change

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating increasing trends or changes in circumstances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ortment
    -0.69
     Donation
    -0.66
    azo
    -0.64
     STL
    -0.64
     caption
    -0.63
    ngth
    -0.63
     naming
    -0.62
     DA
    -0.59
     Alone
    -0.58
     alone
    -0.58
    POSITIVE LOGITS
     fruition
    0.78
     waning
    0.76
    NetMessage
    0.75
    emer
    0.72
    erenn
    0.68
    luster
    0.66
    acerb
    0.65
    tain
    0.65
     evident
    0.65
     prevail
    0.65
    Activations Density 0.547%

    No Known Activations