© 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. 2-RES-JB
    11. 563
    Prev
    Next
    INDEX
    Explanations

    the sequence of letters "ath"

    oai_token-act-pair · gpt-4-turbo

    phrases that contain the suffix "-ath" in them

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of "path" or "ath."

    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
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.78
     Gemini
    -0.70
     shorth
    -0.69
     Reloaded
    -0.66
     Vega
    -0.65
     ESA
    -0.63
     Goff
    -0.60
     Supplemental
    -0.59
     menu
    -0.59
     glitch
    -0.59
    POSITIVE LOGITS
    ath
    1.05
    ouse
    1.00
    aniel
    0.99
    lete
    0.95
    omas
    0.94
    oms
    0.93
    reshold
    0.93
    iop
    0.91
    istle
    0.90
    imer
    0.90
    Activations Density 0.012%

    No Known Activations