© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4-RES-JB
    11. 9564
    Prev
    Next
    INDEX
    Explanations

    the name "Daga" or "Gaga" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Gaga" and its related contexts

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

    No Comments

    Negative Logits
    uple
    -0.71
    most
    -0.69
    points
    -0.67
    ership
    -0.67
     breadth
    -0.66
     pse
    -0.63
    Ö¼
    -0.63
     honesty
    -0.62
    ensible
    -0.62
     backbone
    -0.61
    POSITIVE LOGITS
    vernment
    1.07
     Siren
    0.96
    ption
    0.93
    oka
    0.89
    aga
    0.88
    ña
    0.85
    estro
    0.84
    BILITY
    0.84
    velength
    0.82
    UGH
    0.82
    Activations Density 0.011%

    No Known Activations