© 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. 4-RES-JB
    11. 17024
    Prev
    Next
    INDEX
    Explanations

    chemical elements or compounds, focusing on the element Chromium (Cr)

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Cr" followed by numbers or references to specific compounds

    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
    姫
    -0.92
     Ukrainian
    -0.77
    eers
    -0.76
    folk
    -0.76
     Werewolf
    -0.75
    heid
    -0.75
    HCR
    -0.72
     Georgian
    -0.72
    IELD
    -0.71
    DragonMagazine
    -0.71
    POSITIVE LOGITS
    adle
    1.12
    utch
    1.02
    anks
    0.98
    ump
    0.93
    umb
    0.92
    umin
    0.92
    umbs
    0.91
    uder
    0.89
    udge
    0.89
    acking
    0.88
    Activations Density 0.012%

    No Known Activations