© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 17699
    Prev
    Next
    INDEX
    Explanations

    words related to creation, designation, or identification

    oai_token-act-pair · gpt-3.5-turbo

    words related to processes of creation, formation, or structuring

    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
    dfx
    -0.79
    FTWARE
    -0.65
     glim
    -0.64
     socket
    -0.62
    Moon
    -0.61
    ood
    -0.61
    flame
    -0.60
    Lean
    -0.60
     marrow
    -0.60
    azaki
    -0.58
    POSITIVE LOGITS
    htaking
    0.86
    uated
    0.84
    ating
    0.84
    aukee
    0.82
    onite
    0.78
    ated
    0.77
    SHIP
    0.77
     Prosecut
    0.74
    ropolitan
    0.73
    urally
    0.72
    Activations Density 0.038%

    No Known Activations