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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8-RES-JB
    11. 3197
    Prev
    Next
    INDEX
    Explanations

    sentences that end with the punctuation mark '.'

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks or sentence endings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    interrupted
    -0.80
     severed
    -0.78
     breached
    -0.75
     seamless
    -0.73
     aborted
    -0.73
     landfall
    -0.72
     overhead
    -0.71
     collided
    -0.71
     deton
    -0.70
     obliter
    -0.68
    POSITIVE LOGITS
     Others
    1.48
    Others
    1.22
     Their
    1.17
     They
    1.15
    selves
    1.06
     Personally
    1.03
     Some
    0.98
    They
    0.96
    Their
    0.96
     Especially
    0.96
    Activations Density 0.732%

    No Known Activations