© 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. 20839
    Prev
    Next
    INDEX
    Explanations

    keywords related to a specific subject or entity named "Gy"

    oai_token-act-pair · gpt-3.5-turbo

    references to "Gy" or "gy" 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
    éĹĺ
    -0.96
    ACTED
    -0.86
    ortium
    -0.85
     Hurricanes
    -0.85
    ãģ®éŃĶ
    -0.82
    IBLE
    -0.80
    swick
    -0.79
     Archdemon
    -0.77
    angered
    -0.75
    byter
    -0.73
    POSITIVE LOGITS
    psy
    1.22
    Gy
    1.11
    rosc
    1.04
     gy
    1.02
     Gy
    0.94
    romy
    0.88
    vette
    0.85
    ropy
    0.82
    hett
    0.82
    roid
    0.81
    Activations Density 0.006%

    No Known Activations