© 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. 2491
    Prev
    Next
    INDEX
    Explanations

    links or calls to action within text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Op", likely indicating a focus on operational or organizational contexts

    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
    EngineDebug
    -0.75
    ILLE
    -0.75
    ãĤ¼ãĤ¦ãĤ¹
    -0.75
    ãĥīãĥ©ãĤ´ãĥ³
    -0.73
    ãĤ¨ãĥ«
    -0.73
    =~=~
    -0.69
    åŃIJ
    -0.69
    ãģ¦
    -0.69
    ãģ®éŃĶ
    -0.69
    ARDS
    -0.67
    POSITIVE LOGITS
    Op
    1.11
     Op
    1.07
    osite
    1.03
    yright
    0.99
    aque
    0.99
    etr
    0.94
    ensibly
    0.93
    ober
    0.92
    uph
    0.90
    olicy
    0.90
    Activations Density 0.006%

    No Known Activations