© 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. 12642
    Prev
    Next
    INDEX
    Explanations

    terms related to computer programming and code snippets

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to specific cultural or geographical identities

    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
     reluct
    -0.83
     GOODMAN
    -0.81
    thumbnails
    -0.75
    berman
    -0.73
    HCR
    -0.72
    Demand
    -0.71
    Wheel
    -0.67
    DEBUG
    -0.67
    Contract
    -0.65
    RW
    -0.65
    POSITIVE LOGITS
    ensis
    1.04
     ng
    0.82
    ji
    0.81
    ati
    0.78
     pron
    0.78
    ó
    0.77
    ée
    0.75
     lang
    0.73
    ë
    0.71
    dn
    0.71
    Activations Density 0.524%

    No Known Activations