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. 12429
    Prev
    Next
    INDEX
    Explanations

    company or organization names, possibly related to legal or financial news

    oai_token-act-pair · gpt-3.5-turbo

    instances of parentheses in the text

    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
     langu
    -0.83
     stagn
    -0.76
     offended
    -0.75
     galvan
    -0.74
     onward
    -0.73
    ĪĴ
    -0.72
     clin
    -0.72
     demol
    -0.71
     hijacked
    -0.71
     coales
    -0.71
    POSITIVE LOGITS
    CBC
    1.28
    RELATED
    1.21
    Reporting
    1.19
    Reuters
    1.18
    ANI
    1.15
    Photo
    1.14
    â̦)
    1.07
    PHOTOS
    1.03
    Courtesy
    1.02
    READ
    1.00
    Activations Density 0.044%

    No Known Activations