© 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. 17384
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports competitions

    oai_token-act-pair · gpt-3.5-turbo

    references to rivalries, competition, and related events

    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
    ¾
    -0.80
    ©¶æ¥µ
    -0.80
    Scroll
    -0.72
    tiny
    -0.66
    Redd
    -0.65
    Ĺ
    -0.64
    LIN
    -0.63
    ŀ
    -0.62
    Parameter
    -0.62
    Lay
    -0.62
    POSITIVE LOGITS
     against
    2.27
    against
    2.16
     Against
    1.89
    Against
    1.67
     versus
    1.51
     vs
    1.46
     AGA
    1.21
     Vs
    1.21
    anti
    1.18
    vs
    1.18
    Activations Density 0.282%

    No Known Activations