© 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. 17294
    Prev
    Next
    INDEX
    Explanations

    terms related to notifications or updates

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate notes or annotations

    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
    ãĥ³ãĤ¸
    -0.71
    oÄŁ
    -0.65
    ãĤ¼ãĤ¦ãĤ¹
    -0.64
     Skydragon
    -0.63
     ISBN
    -0.62
     Zombies
    -0.62
    ãĥĩ
    -0.61
     Sims
    -0.61
    «ĺ
    -0.61
     Rez
    -0.60
    POSITIVE LOGITS
    leans
    0.90
    agon
    0.79
    theless
    0.71
    acon
    0.66
    lean
    0.65
    swick
    0.64
    onson
    0.63
    orporated
    0.62
    iance
    0.62
    ermott
    0.61
    Activations Density 0.046%

    No Known Activations