© 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. 2-RES-JB
    11. 12611
    Prev
    Next
    INDEX
    Explanations

    adverbs indicating continuity or affirmation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "still" to indicate continuity or persistence in a situation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     opposite
    -0.77
    é¾
    -0.72
    ãĥ³ãĤ¸
    -0.70
    ocol
    -0.69
    duct
    -0.69
    zag
    -0.67
    %]
    -0.67
    rule
    -0.65
    ultimate
    -0.65
    代
    -0.65
    POSITIVE LOGITS
    Enjoy
    0.79
    ega
    0.76
    noon
    0.75
    heres
    0.73
     retains
    0.72
    alia
    0.71
    birth
    0.70
     Nadu
    0.68
     clinging
    0.68
     Still
    0.68
    Activations Density 0.008%

    No Known Activations