© 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. 6368
    Prev
    Next
    INDEX
    Explanations

    details related to individuals, such as names, ages, positions, and accomplishments

    oai_token-act-pair · gpt-3.5-turbo

    references to player statistics and records in sports contexts

    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
     disadvant
    -0.71
    edition
    -0.70
     monarchy
    -0.69
     Rockefeller
    -0.68
     Confederacy
    -0.66
    Unknown
    -0.66
     Capitalism
    -0.65
     Wendy
    -0.64
     Illuminati
    -0.64
    erity
    -0.64
    POSITIVE LOGITS
     averaged
    1.32
     scored
    1.26
     underwent
    1.22
     joins
    1.16
     tallied
    1.12
     debuted
    1.10
     averages
    1.10
     netted
    1.09
     totaled
    1.09
     struggled
    1.07
    Activations Density 0.244%

    No Known Activations