© 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. 10-RES-JB
    11. 8455
    Prev
    Next
    INDEX
    Explanations

    expressions of sympathy and support for individuals experiencing a loss

    oai_token-act-pair · gpt-3.5-turbo
    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
     quotas
    -0.83
     proficiency
    -0.81
     empir
    -0.80
    tarians
    -0.76
    ensibly
    -0.75
    config
    -0.73
     penetration
    -0.73
    iferation
    -0.71
    iberal
    -0.71
     monopoly
    -0.71
    POSITIVE LOGITS
     grieving
    1.80
     mourning
    1.74
     mourn
    1.72
     condolences
    1.71
     condol
    1.69
     grief
    1.55
     funeral
    1.53
     saddened
    1.45
     sadness
    1.40
     sorrow
    1.39
    Activations Density 0.985%

    No Known Activations