© 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. 3-RES-JB
    11. 9208
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "uber" in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "uber" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥĥãĥī
    -0.76
     Lith
    -0.70
     cob
    -0.66
     abiding
    -0.66
     Boh
    -0.62
     comprom
    -0.62
     Sabha
    -0.61
     compe
    -0.61
     bargaining
    -0.61
    UME
    -0.59
    POSITIVE LOGITS
    culosis
    1.70
    uber
    1.22
    isms
    0.89
    iques
    0.89
    cul
    0.87
    icum
    0.86
    iously
    0.83
    geon
    0.83
    ber
    0.83
    stration
    0.82
    Activations Density 0.007%

    No Known Activations