© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 3-RES-JB
    11. 17244
    Prev
    Next
    INDEX
    Explanations

    terms related to the word "summer"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Symm," which is likely related to a specific context or subject being referenced in the document

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    GROUND
    -0.77
     lawy
    -0.72
    Initialized
    -0.71
     boiled
    -0.71
     boiling
    -0.69
     boil
    -0.69
     kinderg
    -0.62
    dated
    -0.62
     fermented
    -0.61
     dashed
    -0.61
    POSITIVE LOGITS
    mmm
    1.02
    andise
    0.80
    illa
    0.76
    useum
    0.75
    ajor
    0.74
    ud
    0.74
    mm
    0.73
    hair
    0.72
    osexual
    0.72
    ods
    0.71
    Activations Density 0.017%

    No Known Activations