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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1-RES-JB
    11. 24127
    Prev
    Next
    INDEX
    Explanations

    phrases related to projectile weapons and propulsion

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "spell" and its related forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hiba
    -0.79
    udeau
    -0.67
    ocr
    -0.66
    ocard
    -0.61
    Op
    -0.59
    MpServer
    -0.58
     largeDownload
    -0.58
     breadth
    -0.57
    gd
    -0.57
    iscal
    -0.56
    POSITIVE LOGITS
    pelled
    1.42
    pelling
    1.38
    pell
    1.30
    cules
    0.84
    theless
    0.81
    ãĥķãĤ¡
    0.78
    sburg
    0.76
    odox
    0.70
     lev
    0.70
    ress
    0.69
    Activations Density 0.013%

    No Known Activations