© 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. 12567
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Medium"

    oai_token-act-pair · gpt-3.5-turbo

    the word "Medium" and related variations of size descriptors

    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
    çīĪ
    -0.86
     è£ıç
    -0.85
    pher
    -0.79
    ãĤ¡
    -0.78
    utical
    -0.77
    çIJ
    -0.75
    ãĤ©
    -0.75
    soDeliveryDate
    -0.75
    æī
    -0.73
    ãĤ£
    -0.72
    POSITIVE LOGITS
    eus
    0.81
    erity
    0.80
    large
    0.78
    veyard
    0.75
    xus
    0.73
     sized
    0.72
    emo
    0.71
    ounces
    0.71
    uliffe
    0.70
    hap
    0.70
    Activations Density 0.027%

    No Known Activations