© 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. 0-RES-JB
    11. 12305
    Prev
    Next
    INDEX
    Explanations

    mentions of people's birth details

    oai_token-act-pair · gpt-3.5-turbo

    references to birth or the act of being born

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vortex
    -0.69
     utilities
    -0.67
     meter
    -0.65
     loop
    -0.63
     inconvenience
    -0.62
     vendors
    -0.61
     palm
    -0.60
     escalate
    -0.60
     screw
    -0.60
     wrap
    -0.59
    POSITIVE LOGITS
    Born
    3.91
     Born
    3.80
     born
    1.97
    born
    1.90
     Birth
    1.57
    Birth
    1.54
     Married
    1.32
     bom
    1.14
     Daughter
    1.13
     Died
    1.12
    Activations Density 0.019%

    No Known Activations