© 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. 17234
    Prev
    Next
    INDEX
    Explanations

    names related to a specific individual named "Ekman-Larsson."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Ekman" and related 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
    tenance
    -0.88
     اÙĦ
    -0.74
    ACTED
    -0.71
     Ùħ
    -0.70
    >>>>>>>>
    -0.69
    =-=-=-=-=-=-=-=-
    -0.69
     AMERICA
    -0.69
     Clintons
    -0.67
    Ø©
    -0.66
     Continental
    -0.65
    POSITIVE LOGITS
    lund
    0.93
    odox
    0.92
    strom
    0.91
    regate
    0.90
    borg
    0.89
    rand
    0.89
     Ek
    0.88
    sten
    0.87
    wu
    0.87
    daq
    0.86
    Activations Density 0.010%

    No Known Activations