© 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. 4-RES-JB
    11. 6293
    Prev
    Next
    INDEX
    Explanations

    call-to-action prompts at the end of sentences

    oai_token-act-pair · gpt-3.5-turbo

    sentence-ending punctuation or prompts for audience feedback

    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
     footing
    -0.85
     temperament
    -0.80
     antit
    -0.78
     overt
    -0.77
     unaccount
    -0.77
    untarily
    -0.76
     instinct
    -0.75
     involuntary
    -0.74
     fleeing
    -0.72
     suppressed
    -0.72
    POSITIVE LOGITS
     Please
    1.19
     :)
    1.18
     Thanks
    1.15
     Alternatively
    1.13
     However
    1.11
     Additionally
    1.10
     Depending
    1.10
     ;)
    1.08
     Also
    1.08
     Includes
    1.07
    Activations Density 0.713%

    No Known Activations