© 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. 0-RES-JB
    11. 13301
    Prev
    Next
    INDEX
    Explanations

    instances of the word "ent" or variations of the word "ent" such as "entourage" or "enthusiast"

    oai_token-act-pair · gpt-3.5-turbo

    forms of the root word "ent," indicating themes of involvement or engagement

    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
    abase
    -0.69
    fax
    -0.68
    renheit
    -0.67
     Finder
    -0.67
    rx
    -0.65
     Marathon
    -0.65
     printers
    -0.64
     Portable
    -0.64
    aurus
    -0.63
     Played
    -0.63
    POSITIVE LOGITS
     ent
    3.78
     Ent
    1.90
    Ent
    1.63
     entangled
    1.50
     entr
    1.42
     enc
    1.15
     eng
    1.14
     en
    1.14
     tempt
    1.14
     ens
    1.13
    Activations Density 0.017%

    No Known Activations