© 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 EvalsExportsinterp-engineNEWAPI 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. 12-RES-JB
    11. 3229
    Prev
    Next
    INDEX
    Explanations

    words related to a specific brand or product name

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    the repeated sequence "pp" in words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
     Europeans
    -0.56
     wishing
    -0.53
     Kodi
    -0.53
     CW
    -0.52
    âĸ¬âĸ¬
    -0.52
     meager
    -0.52
     annex
    -0.52
     transformative
    -0.51
     losers
    -0.51
     taxpayers
    -0.51
    POSITIVE LOGITS
    lication
    1.36
    earance
    1.27
    erton
    1.18
    arent
    1.17
    enf
    1.17
    enhagen
    1.17
    ucc
    1.15
    atown
    1.10
    olit
    1.08
    elman
    1.06
    Activations Density 0.024%

    No Known Activations