© 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. 9-RES-JB
    11. 3626
    Prev
    Next
    INDEX
    Explanations

    action verbs followed by prepositions

    oai_token-act-pair · gpt-3.5-turbo

    notable shifts in context or focus within narratives

    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
    ãĤ¼ãĤ¦ãĤ¹
    -0.71
    ebted
    -0.67
    Solution
    -0.62
    Products
    -0.61
    assadors
    -0.61
    units
    -0.60
    Effects
    -0.60
    onse
    -0.59
    é¾įåĸļ士
    -0.59
    Therefore
    -0.59
    POSITIVE LOGITS
     typo
    0.69
     Funny
    0.68
     Comedy
    0.68
     Craigslist
    0.66
     Kickstarter
    0.66
     TMZ
    0.60
     silly
    0.60
     limbo
    0.59
     hilarious
    0.59
     weird
    0.59
    Activations Density 0.913%

    No Known Activations