© 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. 4-RES-JB
    11. 2345
    Prev
    Next
    INDEX
    Explanations

    names of specific locations or entities like schools, companies, and cities

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, especially related to locations and organizations

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

    No Comments

    Negative Logits
    lees
    -0.75
    riages
    -0.73
    nels
    -0.68
    urrencies
    -0.68
    assies
    -0.68
    iddles
    -0.67
    anwhile
    -0.67
     Merchants
    -0.66
     embassies
    -0.66
    sites
    -0.66
    POSITIVE LOGITS
     staffer
    0.87
     variant
    0.84
     spokesperson
    0.84
     endorsement
    0.81
    ussian
    0.78
     standpoint
    0.78
     spokeswoman
    0.76
    statement
    0.75
     representative
    0.74
     colleague
    0.73
    Activations Density 0.709%

    No Known Activations