© 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. 13856
    Prev
    Next
    INDEX
    Explanations

    verbs related to actions taken by individuals

    oai_token-act-pair · gpt-3.5-turbo

    action verbs indicating significant occurrences or contributions

    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
    venge
    -0.61
    aging
    -0.58
    yet
    -0.54
    arel
    -0.52
    tile
    -0.51
    thin
    -0.51
    coin
    -0.51
    Trade
    -0.49
    arta
    -0.49
    oro
    -0.48
    POSITIVE LOGITS
    nesday
    0.70
    ĸļ
    0.66
     unsuccessfully
    0.60
    ¿½
    0.59
    raints
    0.57
    ãĤ¤ãĥĪ
    0.56
    monton
    0.55
    ngth
    0.54
     initially
    0.51
     Krug
    0.51
    Activations Density 1.243%

    No Known Activations