© 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. 7680
    Prev
    Next
    INDEX
    Explanations

    phrases related to player transactions in sports

    oai_token-act-pair · gpt-3.5-turbo

    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
     affili
    -0.99
     tremend
    -0.97
     millenn
    -0.90
     concess
    -0.86
     challeng
    -0.86
     perspect
    -0.84
     accomp
    -0.83
    izoph
    -0.82
     corrid
    -0.81
     interf
    -0.81
    POSITIVE LOGITS
     Rookie
    1.36
     Assuming
    1.35
     Teams
    1.33
     However
    1.32
     Considering
    1.31
     Defensive
    1.28
     Hopefully
    1.27
     Unfortunately
    1.27
     Granted
    1.27
     Fans
    1.26
    Activations Density 0.250%

    No Known Activations