© 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. 4-RES-JB
    11. 10597
    Prev
    Next
    INDEX
    Explanations

    names and mentions of a specific person or place, likely "Carm"

    oai_token-act-pair · gpt-3.5-turbo

    the name "Carm" and its variations in different 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
    ãģį
    -0.78
     checkout
    -0.75
     Fargo
    -0.72
    Magikarp
    -0.70
    uating
    -0.68
    lihood
    -0.68
    graduate
    -0.66
    Ń·
    -0.64
    uates
    -0.63
    uation
    -0.63
    POSITIVE LOGITS
    ichael
    1.32
    ageddon
    1.15
    agna
    0.97
    illo
    0.97
    ony
    0.96
    aign
    0.96
    agraph
    0.94
    ando
    0.92
    olin
    0.92
    osh
    0.91
    Activations Density 0.010%

    No Known Activations