© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 17484
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or tasks to be done

    oai_token-act-pair · gpt-3.5-turbo

    sentences that conclude with a period

    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
     carbohyd
    -0.77
    emort
    -0.75
    Þ
    -0.73
     earthqu
    -0.72
     unspecified
    -0.70
     warr
    -0.70
    escription
    -0.70
     millenn
    -0.69
    elaide
    -0.68
    ascus
    -0.68
    POSITIVE LOGITS
     Especially
    1.47
     Suppose
    1.30
     Firstly
    1.29
     Unless
    1.22
     Ideally
    1.21
     Whenever
    1.20
     Anyone
    1.19
     Having
    1.19
     Besides
    1.18
     Imagine
    1.17
    Activations Density 0.482%

    No Known Activations