© 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. 11-RES-JB
    11. 265
    Prev
    Next
    INDEX
    Explanations

    proper nouns, such as names of people and places

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "to be" in various forms

    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
    ramid
    -0.84
    enture
    -0.83
    thumbnails
    -0.78
    pmwiki
    -0.78
     platforms
    -0.76
    Explore
    -0.74
    Vers
    -0.72
    Interstitial
    -0.72
    negie
    -0.72
    issions
    -0.71
    POSITIVE LOGITS
     Ralph
    1.11
     Rodrigo
    1.10
     Cec
    1.10
     Julio
    1.09
     William
    1.08
     Samantha
    1.08
     Jorge
    1.08
     Felix
    1.08
     Matth
    1.08
     Juan
    1.07
    Activations Density 0.165%

    No Known Activations