© 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. 11-RES-JB
    11. 119
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal events or relationships, especially involving emotional or significant moments

    oai_token-act-pair · gpt-3.5-turbo

    possessive forms indicating relationships and ownership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Downloadha
    -0.97
    ernels
    -0.89
    ©¶æ¥µ
    -0.84
    lator
    -0.76
    rypt
    -0.70
    ^{
    -0.70
     Brewer
    -0.69
    yz
    -0.69
    Newsletter
    -0.69
    acket
    -0.67
    POSITIVE LOGITS
     demise
    1.38
     whereabouts
    1.37
     disappearance
    1.37
     departure
    1.36
     fate
    1.31
     plight
    1.24
     resignation
    1.24
     absence
    1.21
     removal
    1.20
     death
    1.18
    Activations Density 0.210%

    No Known Activations