© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 6308
    Prev
    Next
    INDEX
    Explanations

    names or parts of names ending in 'ell'

    oai_token-act-pair · gpt-3.5-turbo

    the word "ell" and its variations in different contexts

    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
     regulate
    -0.68
     constitu
    -0.67
    displayText
    -0.65
     stip
    -0.64
     exha
    -0.64
     deem
    -0.62
    éĹĺ
    -0.62
     guiActiveUn
    -0.62
    lime
    -0.61
     compr
    -0.60
    POSITIVE LOGITS
    owship
    1.25
    iott
    1.15
    ings
    1.02
    agic
    1.01
    ows
    0.95
    inger
    0.94
    ations
    0.94
    baum
    0.92
    otte
    0.91
    atio
    0.91
    Activations Density 0.012%

    No Known Activations