© 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. 12-RES-JB
    11. 2588
    Prev
    Next
    INDEX
    Explanations

    terms related to chemicals and their effects on the body

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    terms related to chemical substances and their effects on health

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orio
    -0.81
    pring
    -0.75
    kus
    -0.74
    hani
    -0.72
    essee
    -0.69
    ruby
    -0.68
    closed
    -0.68
    laus
    -0.66
    ror
    -0.66
    bah
    -0.66
    POSITIVE LOGITS
     concentrations
    1.22
     supplementation
    1.22
     poisoning
    1.18
     deficiency
    1.17
     levels
    1.17
     intoxication
    1.16
     synthesis
    1.14
     depletion
    1.14
     toxicity
    1.10
     secretion
    1.09
    Activations Density 0.168%

    No Known Activations