© 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. 6-RES-JB
    11. 13598
    Prev
    Next
    INDEX
    Explanations

    terms related to entities such as clubs, nations, schools, and teams

    oai_token-act-pair · gpt-3.5-turbo

    nouns associated with entities like teams, nations, schools, and places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    racuse
    -0.72
    tails
    -0.65
    mentioned
    -0.63
     rays
    -0.63
    dos
    -0.62
    tnc
    -0.58
     )]
    -0.57
    eeper
    -0.57
    eus
    -0.56
    undreds
    -0.56
    POSITIVE LOGITS
     indeed
    0.68
     asset
    0.65
     affair
    0.63
     compared
    0.63
    years
    0.63
     withd
    0.63
     devoid
    0.62
     unto
    0.62
    fuck
    0.62
     surrounded
    0.62
    Activations Density 0.243%

    No Known Activations