© 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. 6-RES-JB
    11. 17834
    Prev
    Next
    INDEX
    Explanations

    words related to consecutive events or sequences

    oai_token-act-pair · gpt-3.5-turbo

    key events and significant terms related to legal, political, and historical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BY
    -0.71
    ODE
    -0.68
    Area
    -0.66
    ¶ħ
    -0.65
    NG
    -0.64
    ASE
    -0.62
     pse
    -0.61
    FORE
    -0.61
     Yad
    -0.60
    YP
    -0.60
    POSITIVE LOGITS
     deadline
    0.68
    cation
    0.68
     announcement
    0.64
    emetery
    0.62
    ritz
    0.61
    ires
    0.61
    strom
    0.61
     cutoff
    0.61
     debacle
    0.61
    hower
    0.60
    Activations Density 0.290%

    No Known Activations