© 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. 7860
    Prev
    Next
    INDEX
    Explanations

    references to the Blue Cross organization

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the term "Blue Cross."

    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
     UCH
    -0.79
     Yanuk
    -0.73
    ailable
    -0.72
    ENCY
    -0.70
    acious
    -0.68
    otor
    -0.67
    EMBER
    -0.65
     Gupta
    -0.64
     "$:/
    -0.63
    IND
    -0.63
    POSITIVE LOGITS
    roads
    1.28
    bones
    1.00
    Cross
    0.96
    bows
    0.90
    fax
    0.88
    es
    0.85
     Sakuya
    0.85
     Cross
    0.83
    cross
    0.81
    Fit
    0.80
    Activations Density 0.017%

    No Known Activations