© 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. 1282
    Prev
    Next
    INDEX
    Explanations

    words related to locations or places

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "or"

    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
     msec
    -0.60
    OTAL
    -0.60
    Fra
    -0.60
    eas
    -0.59
    assadors
    -0.59
    inctions
    -0.58
    SPONSORED
    -0.56
    SPA
    -0.56
    Wall
    -0.55
    pter
    -0.54
    POSITIVE LOGITS
    ific
    1.08
    chid
    1.06
    phans
    1.05
    izons
    1.02
    andom
    1.00
    ussia
    0.97
    ikawa
    0.96
    onto
    0.95
    thodox
    0.94
    acle
    0.90
    Activations Density 0.028%

    No Known Activations