© 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. 13780
    Prev
    Next
    INDEX
    Explanations

    the word "Grand" followed by a digit

    oai_token-act-pair · gpt-3.5-turbo

    references to "Grand" locations or entities

    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
    lihood
    -0.86
    ople
    -0.75
    yip
    -0.73
    qqa
    -0.72
    agen
    -0.71
    PsyNetMessage
    -0.70
    ologies
    -0.68
     numbered
    -0.64
     pse
    -0.64
     plur
    -0.64
    POSITIVE LOGITS
    father
    1.34
     Prix
    1.32
    mother
    1.29
    parents
    1.22
    pa
    1.15
     Theft
    1.11
     Rapids
    1.10
    master
    1.05
    addy
    1.02
    parent
    1.00
    Activations Density 0.012%

    No Known Activations