© 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. 10049
    Prev
    Next
    INDEX
    Explanations

    terms related to investigations, probes, or inquiries into various subjects and individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to political investigations and scandals

    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
    ĺħ
    -0.89
    anguage
    -0.80
    advant
    -0.76
    ç·
    -0.75
    Artist
    -0.74
    tml
    -0.73
    ãĥ´
    -0.71
    oS
    -0.70
    */(
    -0.70
    chall
    -0.70
    POSITIVE LOGITS
     dealings
    1.16
     mishand
    1.11
     finances
    1.02
     misconduct
    0.97
     handling
    0.95
     scandals
    0.94
     affair
    0.94
     alleged
    0.93
     bribery
    0.93
     improperly
    0.91
    Activations Density 0.493%

    No Known Activations