© 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. 3-RES-JB
    11. 18354
    Prev
    Next
    INDEX
    Explanations

    phrases related to locations or organizations

    oai_token-act-pair · gpt-3.5-turbo

    frequently occurring suffixes and tokens commonly associated with names and places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MW
    -0.71
    ``
    -0.69
     magnification
    -0.64
     kW
    -0.64
     fray
    -0.64
    fighters
    -0.62
     hereafter
    -0.61
     <+
    -0.61
    called
    -0.60
     Instruct
    -0.60
    POSITIVE LOGITS
    ibrary
    0.76
    steen
    0.76
    phia
    0.73
    stad
    0.71
    zan
    0.69
    eros
    0.65
    idge
    0.65
    acus
    0.65
    oise
    0.64
    stead
    0.63
    Activations Density 0.255%

    No Known Activations