© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 0-RES-JB
    11. 13813
    Prev
    Next
    INDEX
    Explanations

    phrases related to pharmaceuticals or chemical compounds

    oai_token-act-pair · gpt-3.5-turbo

    acronyms or abbreviations related to health and medical fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lamb
    -0.73
    resents
    -0.70
     seams
    -0.69
     sett
    -0.69
     Eston
    -0.66
    ä
    -0.66
    adows
    -0.66
    estern
    -0.65
     Lent
    -0.64
    ãĥĺ
    -0.64
    POSITIVE LOGITS
     PH
    3.69
    PH
    2.33
    Ph
    1.85
     Ph
    1.53
     ph
    1.43
     PHI
    1.42
    ph
    1.41
     Phant
    1.27
     PD
    1.27
     MH
    1.22
    Activations Density 0.030%

    No Known Activations