© 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. 21644
    Prev
    Next
    INDEX
    Explanations

    prepositions "for" in contexts of advocating, arguing, discussing, pressing, and other similar activities

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate durations of time or periods for which something has been occurring

    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
    ãĥ¯ãĥ³
    -0.71
    ucker
    -0.70
    rue
    -0.70
    âĨij
    -0.69
    ivo
    -0.66
    ´
    -0.65
    ä½ľ
    -0.65
    ranch
    -0.64
    Movie
    -0.64
    eye
    -0.63
    POSITIVE LOGITS
     years
    1.80
     decades
    1.74
     months
    1.68
     weeks
    1.48
     centuries
    1.40
     awhile
    1.36
     millennia
    1.28
    years
    1.28
     YEAR
    1.27
    months
    1.27
    Activations Density 0.227%

    No Known Activations