© 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. 4-RES-JB
    11. 1511
    Prev
    Next
    INDEX
    Explanations

    specific terms or phrases related to various tools, symbols, facilities, and gadgets

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various types of objects or concepts

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

    No Comments

    Negative Logits
    thood
    -0.69
    ilaterally
    -0.67
    vae
    -0.63
    ;;;;
    -0.63
    azeera
    -0.60
    Lago
    -0.58
    DonaldTrump
    -0.58
    ecause
    -0.56
    itored
    -0.56
    stasy
    -0.55
    POSITIVE LOGITS
    iest
    0.77
     itself
    0.72
     portion
    0.60
    ultimate
    0.57
     operator
    0.56
     revolves
    0.56
     keyword
    0.55
     mechanic
    0.55
     succeeded
    0.54
     furthe
    0.54
    Activations Density 0.993%

    No Known Activations