© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 21760
    Prev
    Next
    INDEX
    Explanations

    notifications or being informed about actions or events

    oai_token-act-pair · gpt-3.5-turbo

    references to notifications and the act of informing others

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    igham
    -0.68
    uckles
    -0.66
     ILCS
    -0.66
     metaphors
    -0.65
     wisely
    -0.61
     goggles
    -0.61
     rug
    -0.60
    chieve
    -0.60
     Gabe
    -0.59
    rylic
    -0.59
    POSITIVE LOGITS
     impending
    1.24
     arrival
    0.98
     imminent
    0.87
     whereabouts
    0.84
     wrongdoing
    0.72
     beforehand
    0.72
    ident
    0.71
     incoming
    0.71
     inacc
    0.70
     dismissal
    0.69
    Activations Density 0.209%

    No Known Activations