© 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. 7-RES-JB
    11. 3623
    Prev
    Next
    INDEX
    Explanations

    references to misinformation or deception

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "fake" related to misinformation or deceptive content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xual
    -0.99
    ands
    -0.77
    bard
    -0.75
    ires
    -0.72
    ĸļ
    -0.71
    onen
    -0.71
    pour
    -0.69
    ishops
    -0.69
    anded
    -0.69
    hens
    -0.68
    POSITIVE LOGITS
    ument
    0.88
     pas
    0.86
     IDs
    0.80
    ulent
    0.72
    outs
    0.70
    gery
    0.69
     positives
    0.69
    ²¾
    0.68
     tan
    0.67
    ulously
    0.66
    Activations Density 0.034%

    No Known Activations