© 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. 9-RES-JB
    11. 2308
    Prev
    Next
    INDEX
    Explanations

    references to financial institutions, particularly Fannie Mae and Freddie Mac

    oai_token-act-pair · gpt-3.5-turbo

    mentions of government-sponsored mortgage companies and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uality
    -0.88
    ophon
    -0.84
    ory
    -0.83
    otropic
    -0.82
    icles
    -0.82
    ograph
    -0.82
    icho
    -0.82
    ingen
    -0.81
    ozy
    -0.80
    aran
    -0.80
    POSITIVE LOGITS
     Mae
    1.00
     Freddie
    0.78
     Mercury
    0.73
     Luck
    0.72
     Gray
    0.71
     Mac
    0.69
     Nav
    0.68
     McF
    0.67
     Gibbs
    0.67
     DeVos
    0.66
    Activations Density 0.118%

    No Known Activations