© 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. 15539
    Prev
    Next
    INDEX
    Explanations

    names or terms that things are commonly known or referred to as

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the word "referred" along with their references or identifiers

    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
    iscopal
    -0.68
    edom
    -0.58
    ointment
    -0.58
     Skydragon
    -0.57
     foreseeable
    -0.55
    vale
    -0.55
    smanship
    -0.55
    performance
    -0.55
    lahoma
    -0.54
    uala
    -0.52
    POSITIVE LOGITS
     herein
    0.84
     hereafter
    0.81
     derog
    0.78
    ãĥ¼ãĥ³
    0.76
    literally
    0.74
    okingly
    0.72
     as
    0.72
     pronouns
    0.70
     euphem
    0.69
     "{
    0.69
    Activations Density 0.086%

    No Known Activations