© 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. 8-RES-JB
    11. 17677
    Prev
    Next
    INDEX
    Explanations

    mentions of the news network CNN

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the news network CNN

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    phant
    -0.76
    pell
    -0.73
    hot
    -0.70
    hend
    -0.66
    mits
    -0.66
    plates
    -0.65
    ocene
    -0.65
    metic
    -0.62
    axy
    -0.62
    hens
    -0.62
    POSITIVE LOGITS
    Money
    1.29
    NOW
    1.05
     affiliate
    1.00
    ILLE
    0.90
    pedia
    0.90
     anchor
    0.86
    iliate
    0.84
    IVERS
    0.82
    NEWS
    0.82
    CNN
    0.80
    Activations Density 0.029%

    No Known Activations