© 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. 13012
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names, specifically the name "Charles"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Charles."

    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
    vr
    -0.84
    VR
    -0.82
    HD
    -0.74
    HR
    -0.73
    zb
    -0.72
    medi
    -0.70
    gamer
    -0.68
    hw
    -0.67
    HUD
    -0.67
    zn
    -0.67
    POSITIVE LOGITS
     Charles
    3.34
    Charles
    2.93
     Charlie
    1.57
     Louis
    1.56
     Chuck
    1.51
     William
    1.49
     Claude
    1.48
     Francis
    1.42
     Richard
    1.40
     Francois
    1.38
    Activations Density 0.014%

    No Known Activations