© 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. 0-RES-JB
    11. 11906
    Prev
    Next
    INDEX
    Explanations

    phrases related to the name "Fell"

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Fell" and various types of fellowships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    commerce
    -0.67
     Hash
    -0.65
     Terr
    -0.65
    Sim
    -0.64
    ItemImage
    -0.63
     Rousse
    -0.62
    uminium
    -0.62
     retailer
    -0.62
    ordering
    -0.61
     Dynam
    -0.61
    POSITIVE LOGITS
     Fell
    3.17
     fellows
    2.65
     Fellowship
    2.56
     fellowship
    2.47
     Fellow
    2.40
    owship
    1.48
    doctoral
    1.40
    fell
    1.21
     Perkins
    1.21
     Scholars
    1.21
    Activations Density 0.052%

    No Known Activations