© 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. 11-RES-JB
    11. 20487
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal or academic discourse

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, especially periods at the end of sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     glim
    -1.07
     volunte
    -0.89
     neighb
    -0.87
     reluct
    -0.86
     satell
    -0.86
     gobl
    -0.84
     strugg
    -0.84
     powering
    -0.84
     entreprene
    -0.82
     unden
    -0.80
    POSITIVE LOGITS
     Similarly
    1.60
     Furthermore
    1.52
     Moreover
    1.48
     Likewise
    1.46
     Additionally
    1.42
     Nevertheless
    1.40
     Nonetheless
    1.39
     Presumably
    1.36
     Thus
    1.35
     Consequently
    1.33
    Activations Density 0.554%

    No Known Activations