© 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. 2268
    Prev
    Next
    INDEX
    Explanations

    keywords related to news reporting and social media interactions

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to reporting or disclosing information

    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
    ngth
    -0.87
    umerous
    -0.81
    ĸļ
    -0.80
    terness
    -0.76
     foremost
    -0.75
     teasp
    -0.71
    alyst
    -0.70
    ridor
    -0.70
    allion
    -0.69
    achus
    -0.69
    POSITIVE LOGITS
     anything
    1.01
     something
    0.99
     stuff
    0.98
     GMOs
    0.95
     abortions
    0.93
     things
    0.89
     THEIR
    0.88
     abortion
    0.87
     boobs
    0.85
     contraceptives
    0.85
    Activations Density 0.546%

    No Known Activations