© 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. 5293
    Prev
    Next
    INDEX
    Explanations

    phrases where someone is mentioned as preferring not to be identified or named

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating requests for anonymity or confidentiality

    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
     Orn
    -0.66
    warm
    -0.64
     Arri
    -0.63
    hyde
    -0.63
    Ļ½
    -0.62
    chrome
    -0.58
    almost
    -0.56
     chopping
    -0.55
     Tend
    -0.54
     majorities
    -0.54
    POSITIVE LOGITS
     name
    1.01
     pseudonym
    0.97
     surname
    0.96
     names
    0.89
     named
    0.85
     anonymity
    0.85
     attribution
    0.82
     repr
    0.81
    named
    0.80
     identified
    0.79
    Activations Density 0.066%

    No Known Activations