© 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. 4-RES-JB
    11. 4139
    Prev
    Next
    INDEX
    Explanations

    terms related to legal issues, particularly child pornography and voter fraud

    oai_token-act-pair · gpt-3.5-turbo

    terms related to child exploitation and voter fraud

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

    No Comments

    Negative Logits
    SN
    -0.83
    Ô
    -0.80
    Travel
    -0.71
    é¾įåĸļ士
    -0.71
    FI
    -0.70
     Feather
    -0.69
    El
    -0.69
    åĬ
    -0.69
    rawdownloadcloneembedreportprint
    -0.68
    stown
    -0.68
    POSITIVE LOGITS
     prevention
    0.93
     incarcer
    0.85
    culosis
    0.76
     disproportion
    0.75
     epidemic
    0.74
     shaming
    0.73
     arrests
    0.73
     hysteria
    0.72
     disadvant
    0.72
     prosecutions
    0.72
    Activations Density 0.212%

    No Known Activations