© 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 EvalsExportsinterp-engineNEWAPI 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. 2-RES-JB
    11. 4558
    Prev
    Next
    INDEX
    Explanations

    words related to geographical locations and specific names

    oai_token-act-pair · gpt-3.5-turbo

    references to specific athletes, particularly their names and related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ¥ŀ
    -0.86
    tails
    -0.85
     exha
    -0.79
    ©¶æ
    -0.74
    ilee
    -0.71
    chwitz
    -0.70
     Tsukuyomi
    -0.68
    accompan
    -0.68
    ©¶æ¥µ
    -0.67
     domin
    -0.66
    POSITIVE LOGITS
    ting
    0.87
    Reloaded
    0.85
    wark
    0.85
    gery
    0.84
    ters
    0.79
    umbnail
    0.76
    geries
    0.75
    ted
    0.74
    tenance
    0.73
    aque
    0.72
    Activations Density 0.022%

    No Known Activations