© 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. 2-RES-JB
    11. 11752
    Prev
    Next
    INDEX
    Explanations

    references to various versions or forms of the word "mans."

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "man" and its variations in the context of people or characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĨij
    -0.84
    RAY
    -0.72
    Reviewer
    -0.70
     Archdemon
    -0.70
     promoters
    -0.66
    OPLE
    -0.65
     crawl
    -0.64
    ISM
    -0.64
    AKING
    -0.63
     promoter
    -0.62
    POSITIVE LOGITS
    pread
    1.20
    mans
    1.20
    creen
    1.19
    terday
    1.02
    ault
    0.98
    hirt
    0.91
    manship
    0.90
    peed
    0.89
    sels
    0.89
    ions
    0.89
    Activations Density 0.010%

    No Known Activations