Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 11699
    Prev
    Next
    INDEX
    Explanations

    texts related to news and analysis, particularly focused on Israel, the Middle East, and the Jewish world

    oai_token-act-pair · gpt-3.5-turbo

    references to geopolitical regions and related sociopolitical issues

    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
    soever
    -0.77
    ealous
    -0.72
    ecause
    -0.70
     elig
    -0.64
    igslist
    -0.64
     ordinances
    -0.64
    gom
    -0.62
     ordinance
    -0.62
    Footnote
    -0.60
    lease
    -0.60
    POSITIVE LOGITS
    podcast
    0.66
    Science
    0.62
    Ñı
    0.57
    waves
    0.55
    etry
    0.54
    ä¹
    0.53
    currency
    0.53
     itself
    0.53
     ourselves
    0.52
    ubuntu
    0.52
    Activations Density 0.083%

    No Known Activations