© 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. 9-RES-JB
    11. 7553
    Prev
    Next
    INDEX
    Explanations

    words related to statements or claims being made

    oai_token-act-pair · gpt-3.5-turbo

    statements or comments made by individuals in a reporting context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EDIT
    -0.71
    irs
    -0.66
    ktop
    -0.64
    ï¸
    -0.64
    Justice
    -0.62
    soType
    -0.60
    xtap
    -0.60
    gencies
    -0.60
    terness
    -0.60
     GOODMAN
    -0.60
    POSITIVE LOGITS
     "[
    0.91
     "âĢ¦
    0.88
     omin
    0.75
     bluntly
    0.72
     '[
    0.72
     aloud
    0.72
     "#
    0.70
     publicly
    0.68
     underestimated
    0.66
     Saddam
    0.65
    Activations Density 0.389%

    No Known Activations