© 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. 10-RES-JB
    11. 3297
    Prev
    Next
    INDEX
    Explanations

    phrases related to family members and relatives

    oai_token-act-pair · gpt-3.5-turbo

    terms related to family and relatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Cola
    -0.76
    lite
    -0.75
    Effective
    -0.72
    inently
    -0.69
    Indust
    -0.66
    avery
    -0.64
    Thumbnail
    -0.64
    Auth
    -0.62
    rection
    -0.61
    yss
    -0.61
    POSITIVE LOGITS
     whom
    0.99
     relatives
    0.97
     who
    0.97
    hips
    0.95
     grieving
    0.94
     deceased
    0.91
     reunion
    0.88
     caregivers
    0.87
     mourn
    0.85
     mourning
    0.84
    Activations Density 0.088%

    No Known Activations