© 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. 10-RES-JB
    11. 20516
    Prev
    Next
    INDEX
    Explanations

    phrases related to the US Securities and Exchange Commission (SEC)

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Securities and Exchange Commission (SEC)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itarian
    -0.95
    ciation
    -0.89
    lihood
    -0.86
    hy
    -0.67
    liness
    -0.66
    ience
    -0.65
    hist
    -0.65
    hood
    -0.65
    hs
    -0.65
    spell
    -0.64
    POSITIVE LOGITS
    OND
    1.39
    RET
    1.28
    urities
    1.07
    UR
    0.90
    ratulations
    0.88
    DEF
    0.87
    ON
    0.86
    URE
    0.84
    emetery
    0.83
    ENSE
    0.82
    Activations Density 0.030%

    No Known Activations