© 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. 17314
    Prev
    Next
    INDEX
    Explanations

    instances of the word "salt" in the text

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "salt."

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    merce
    -0.84
     [|
    -0.70
    pload
    -0.69
    STEP
    -0.69
     UNHCR
    -0.67
    vernment
    -0.67
    orne
    -0.66
    psc
    -0.65
     Orders
    -0.65
    =-=-=-=-
    -0.64
    POSITIVE LOGITS
     salt
    1.08
    water
    1.00
     iod
    0.92
    iness
    0.92
     salts
    0.89
     baths
    0.87
    Salt
    0.86
    bite
    0.80
    iest
    0.77
    pick
    0.77
    Activations Density 0.007%

    No Known Activations