© 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. 3-RES-JB
    11. 3641
    Prev
    Next
    INDEX
    Explanations

    phrases related to photography and technological terms

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "log" and its related forms, indicating a focus on logging or documentation themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    theless
    -0.75
    xual
    -0.69
    ETHOD
    -0.68
    ãĥĨãĤ£
    -0.66
    ULTS
    -0.65
    URRENT
    -0.65
     cour
    -0.64
    terday
    -0.64
    riages
    -0.64
    ãĤ¼ãĤ¦ãĤ¹
    -0.63
    POSITIVE LOGITS
    ging
    1.45
    gers
    1.37
    ged
    1.17
    ger
    1.15
    istics
    1.11
    istical
    1.10
    itech
    1.03
    ical
    1.02
    istically
    1.01
    gment
    0.97
    Activations Density 0.011%

    No Known Activations