© 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. 1-RES-JB
    11. 15948
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Res" with high activation levels

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Res," often related to respect or recognition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    glers
    -0.74
    aneers
    -0.71
     Sark
    -0.71
    rious
    -0.66
     Wilhelm
    -0.64
     CMS
    -0.62
     Pf
    -0.60
    =-=-=-=-=-=-=-=-
    -0.59
     Bah
    -0.59
    tips
    -0.59
    POSITIVE LOGITS
    istance
    1.24
    olution
    1.14
    olver
    1.05
    urrection
    1.05
    lict
    1.04
    istant
    1.04
    ailability
    1.03
    olve
    1.01
    Res
    1.01
    idential
    0.99
    Activations Density 0.008%

    No Known Activations