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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 0-RES-JB
    6. 7385
    Prev
    Next
    INDEX
    Explanations

    terms related to the 20th century

    oai_token-act-pair · gpt-3.5-turbo

    references to the 20th century and associated themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Jail
    -0.72
     bust
    -0.70
     flexibility
    -0.66
     options
    -0.66
     Scout
    -0.65
     Flex
    -0.65
     head
    -0.64
     leverage
    -0.62
     CAP
    -0.62
     distraction
    -0.62
    POSITIVE LOGITS
    ieth
    5.26
    eenth
    1.76
    aughters
    1.28
    ies
    1.22
    iest
    1.16
    ilee
    1.10
    idth
    1.03
    elfth
    1.02
    enth
    1.01
    ied
    1.00
    Activations Density 0.010%

    No Known Activations