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. 4-RES-JB
    6. 10287
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to historical and political contexts, specifically pertaining to the term "Reich" and entities like "Bundesbank" from Germany

    oai_token-act-pair · gpt-3.5-turbo

    references to historical entities related to the German Reich or governmental institutions

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

    No Comments

    Negative Logits
    ctica
    -0.76
    neau
    -0.70
    acity
    -0.67
    thumbnails
    -0.66
    Downloadha
    -0.66
    abetic
    -0.65
    Hop
    -0.65
    ILA
    -0.65
     Heavenly
    -0.64
     Tibetan
    -0.64
    POSITIVE LOGITS
    hardt
    1.07
     Reich
    1.01
    stein
    0.88
    lich
    0.88
    wald
    0.84
    ynski
    0.84
    fried
    0.82
    enstein
    0.81
     decree
    0.81
    itzer
    0.78
    Activations Density 0.011%

    No Known Activations