© 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. 2-RES-JB
    11. 13661
    Prev
    Next
    INDEX
    Explanations

    references to locations or entities associated with the abbreviation "DE"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific entities or abbreviations, particularly related to 'DE' and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¤ãĥĪ
    -0.99
    oulos
    -0.83
    toggle
    -0.83
    andise
    -0.82
    ãĤ¹ãĥĪ
    -0.81
    ocene
    -0.78
    hetti
    -0.77
    ãĤ±
    -0.70
    eele
    -0.70
     Meier
    -0.69
    POSITIVE LOGITS
    FAULT
    1.16
    VICE
    1.11
    ATH
    1.01
    FIN
    0.99
    POS
    0.99
    VEL
    0.93
    VE
    0.86
    GE
    0.86
    DE
    0.86
    PUT
    0.83
    Activations Density 0.007%

    No Known Activations