© 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. 0-RES-JB
    11. 16519
    Prev
    Next
    INDEX
    Explanations

    references to a specific name or person, particularly "Ivanka."

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Clicker
    -0.83
     stere
    -0.78
     puzz
    -0.76
     Camer
    -0.70
     rapt
    -0.70
     Clim
    -0.70
     hig
    -0.69
     Kling
    -0.68
    Wheel
    -0.68
     Hallow
    -0.67
    POSITIVE LOGITS
    anka
    2.35
    ANA
    2.15
    ña
    2.12
    anya
    2.06
    aja
    2.05
    enna
    1.81
    itta
    1.70
    acha
    1.68
    apa
    1.68
    vana
    1.64
    Activations Density 0.027%

    No Known Activations