© 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. 20412
    Prev
    Next
    INDEX
    Explanations

    proper names

    oai_token-act-pair · gpt-3.5-turbo

    repeated names or references to individuals

    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
     offline
    -0.74
     Korra
    -0.73
     Manip
    -0.68
     overseas
    -0.68
     wow
    -0.67
     Important
    -0.66
     Yoga
    -0.64
     Naruto
    -0.63
     Rebirth
    -0.63
     numbered
    -0.63
    POSITIVE LOGITS
    isner
    1.55
    idel
    1.35
    iber
    1.32
    ffer
    1.27
    iman
    1.26
    hner
    1.26
    aney
    1.24
    isel
    1.23
    cker
    1.20
    hn
    1.19
    Activations Density 0.081%

    No Known Activations