© 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. 9-RES-JB
    11. 17882
    Prev
    Next
    INDEX
    Explanations

    legal and administrative terms related to agreements, orders, and procedures

    oai_token-act-pair · gpt-3.5-turbo

    terms related to collaborative efforts and organizational structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bernatorial
    -0.82
    ropolis
    -0.66
    nai
    -0.64
    ippery
    -0.64
    ãĤ¨ãĥ«
    -0.62
     skyline
    -0.61
    irlf
    -0.59
    anamo
    -0.58
    ghazi
    -0.58
    amina
    -0.57
    POSITIVE LOGITS
     alone
    1.02
     rather
    0.83
     techniques
    0.74
     or
    0.74
    rather
    0.73
     supplemented
    0.72
     technique
    0.71
     infusion
    0.68
    .[
    0.68
     pioneered
    0.68
    Activations Density 0.548%

    No Known Activations