© 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. 16967
    Prev
    Next
    INDEX
    Explanations

    dates when things were released

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "released," specifically in the context of media or products

    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
    anan
    -0.75
    isma
    -0.72
    stal
    -0.68
    ophe
    -0.67
    aque
    -0.66
    iop
    -0.65
    orum
    -0.64
     Trou
    -0.61
    iron
    -0.61
    mad
    -0.61
    POSITIVE LOGITS
    éĹĺ
    0.98
    released
    0.91
    æĸ¹
    0.91
     releasing
    0.87
    Release
    0.83
    quished
    0.81
    ãĥ´
    0.80
     RELEASE
    0.79
     release
    0.79
    Released
    0.78
    Activations Density 0.037%

    No Known Activations