© 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. 7-RES-JB
    11. 22737
    Prev
    Next
    INDEX
    Explanations

    proper nouns and numerical identifiers

    oai_token-act-pair · gpt-3.5-turbo

    references to identification of individuals in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    issance
    -0.82
     enjoyment
    -0.72
    yrim
    -0.70
    eries
    -0.70
     stagnation
    -0.67
    tumblr
    -0.66
    lag
    -0.66
    gard
    -0.66
     stagn
    -0.65
    psey
    -0.64
    POSITIVE LOGITS
     surn
    0.95
     alias
    0.93
     deceased
    0.86
     pseudonym
    0.82
     redacted
    0.81
     Tsarnaev
    0.80
    Rus
    0.79
     Cosponsors
    0.78
     Identified
    0.76
    ACTED
    0.76
    Activations Density 0.114%

    No Known Activations