© 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. 1-RES-JB
    11. 3399
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to the name "Carson"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the person "Carson"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    */(
    -0.84
    dayName
    -0.83
    "]=>
    -0.82
    lihood
    -0.81
    д
    -0.72
    ~~~~~~~~~~~~~~~~
    -0.70
     CTRL
    -0.69
    URI
    -0.68
    olphins
    -0.67
     newsp
    -0.66
    POSITIVE LOGITS
     Carson
    1.29
    arson
    0.98
     Palmer
    0.96
     Went
    0.90
     Daly
    0.85
    jriwal
    0.82
    hurst
    0.80
    illo
    0.79
    itus
    0.79
    anan
    0.78
    Activations Density 0.007%

    No Known Activations