© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4-RES-JB
    11. 24236
    Prev
    Next
    INDEX
    Explanations

    phrases related to legislation, infringement, and regulations

    oai_token-act-pair · gpt-3.5-turbo

    sections of text with specific formatting or symbols, suggesting a focus on unconventional typography or characters

    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
    ussian
    -0.75
    omething
    -0.71
    iolet
    -0.69
    secut
    -0.65
    enta
    -0.62
    lda
    -0.62
     sled
    -0.62
     Somerset
    -0.61
     tremend
    -0.61
     Manhattan
    -0.61
    POSITIVE LOGITS
    ¬
    0.87
    âĹ¼
    0.81
    âĢł
    0.79
    £
    0.74
    ¹
    0.73
    Û
    0.72
    atures
    0.72
    catentry
    0.72
    Spons
    0.72
    price
    0.70
    Activations Density 0.433%

    No Known Activations