© 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. 9-RES-JB
    11. 18481
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a time reference from the past

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "long before."

    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
    wich
    -0.72
    gallery
    -0.70
    atic
    -0.69
    ¸
    -0.68
    arse
    -0.68
    dale
    -0.68
    cheat
    -0.68
    âĵĺ
    -0.67
    ield
    -0.67
    <?
    -0.67
    POSITIVE LOGITS
     anyone
    1.10
     anybody
    0.99
     any
    0.91
     anything
    0.88
     ANY
    0.83
     existed
    0.79
     Gutenberg
    0.73
     advent
    0.72
     neocons
    0.71
     mattered
    0.71
    Activations Density 0.086%

    No Known Activations