© 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. 2-RES-JB
    11. 17685
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to political figures or events being announced or revealed

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "unveiled."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onz
    -0.72
    unker
    -0.71
    pmwiki
    -0.68
    die
    -0.68
     coli
    -0.66
    avery
    -0.62
    osate
    -0.61
    tem
    -0.59
    bel
    -0.59
    MQ
    -0.59
    POSITIVE LOGITS
     unveiled
    1.18
     unveiling
    1.10
     unveil
    1.05
    nesday
    0.96
     showc
    0.95
    éĹĺ
    0.90
    announced
    0.85
     announcements
    0.83
    urated
    0.81
     announces
    0.78
    Activations Density 0.015%

    No Known Activations