© 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 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. 2-RES-JB
    11. 14504
    Prev
    Next
    INDEX
    Explanations

    words related to kinship and connection between people

    oai_token-act-pair · gpt-3.5-turbo

    words indicating relationships or connections between people or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atra
    -0.75
    eva
    -0.71
    uden
    -0.71
    utic
    -0.69
    ©¶æ
    -0.67
    atton
    -0.67
    omy
    -0.67
    NN
    -0.67
    atche
    -0.66
    ighth
    -0.66
    POSITIVE LOGITS
     kindred
    1.21
     spirits
    1.05
     strugg
    0.83
     souls
    0.82
     kins
    0.80
     Vessel
    0.78
    luaj
    0.75
     Instruments
    0.72
     fractions
    0.70
     vein
    0.70
    Activations Density 0.005%

    No Known Activations