© 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. 10520
    Prev
    Next
    INDEX
    Explanations

    news agencies

    oai_token-act-pair · gpt-3.5-turbo

    references to news agencies and reporting

    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
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.80
    etsy
    -0.71
    0000000000000000
    -0.67
    avery
    -0.66
    âķIJ
    -0.66
    come
    -0.64
    paces
    -0.64
    zees
    -0.63
    urden
    -0.63
     stagnation
    -0.63
    POSITIVE LOGITS
     outlets
    1.01
     outlet
    0.98
     quoted
    0.92
     aired
    0.87
     quotes
    0.86
     quoting
    0.86
     reporter
    0.83
     reports
    0.83
     TMZ
    0.82
     broadcasts
    0.79
    Activations Density 0.086%

    No Known Activations