© 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. 4-RES-JB
    11. 21987
    Prev
    Next
    INDEX
    Explanations

    references to the geographical location "Punjab."

    oai_token-act-pair · gpt-3.5-turbo

    references to the Punjab region

    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
    psey
    -0.72
    wine
    -0.67
     principals
    -0.66
     leash
    -0.66
    SUP
    -0.65
    bell
    -0.63
    roll
    -0.63
    ment
    -0.63
    TAG
    -0.63
     dys
    -0.62
    POSITIVE LOGITS
     Plain
    0.80
    ãĥ¼ãĥĨãĤ£
    0.79
     ILCS
    0.77
    ãĤ¤ãĥĪ
    0.75
    otaur
    0.74
    itor
    0.72
    ãĥ©ãĥ³
    0.72
     miscar
    0.72
    ãĥĥãĥĪ
    0.71
    ãĥ¬
    0.71
    Activations Density 0.022%

    No Known Activations