© 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. 4-RES-JB
    11. 10179
    Prev
    Next
    INDEX
    Explanations

    proper names that contain the substring "yd" or "gd"

    oai_token-act-pair · gpt-3.5-turbo

    recurring patterns of the letters "yd" in various 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
     resolve
    -0.69
    ça
    -0.67
     caution
    -0.67
     deaf
    -0.66
    Xi
    -0.63
     FIRE
    -0.62
    xon
    -0.62
     pity
    -0.61
     perfect
    -0.61
    voy
    -0.61
    POSITIVE LOGITS
    aniel
    1.08
    roxy
    1.04
    roid
    0.98
    rox
    0.96
    essert
    0.96
    ynamic
    0.92
    ynam
    0.92
    yd
    0.90
    ere
    0.90
    iamond
    0.89
    Activations Density 0.008%

    No Known Activations