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

    Neuronpedia

    Jacobian LensNEW
    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. 0-RES-JB
    11. 12607
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Carlson" in various contexts, possibly related to news coverage or individuals

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Carlson."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     Palestinians
    -0.77
     POW
    -0.75
     Pip
    -0.74
     Wine
    -0.74
     PSP
    -0.74
    Palest
    -0.74
     Pledge
    -0.73
    pipe
    -0.73
     pipe
    -0.72
     PA
    -0.72
    POSITIVE LOGITS
     Carlson
    3.65
    Carl
    2.90
     Carlton
    1.95
     Carl
    1.25
     Tucker
    1.16
    elong
    1.13
     Daly
    1.08
     Carlos
    1.02
     Lob
    1.01
    chell
    0.98
    Activations Density 0.040%

    No Known Activations