© 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. 11371
    Prev
    Next
    INDEX
    Explanations

    phrases related to personnel assignments or groupings

    oai_token-act-pair · gpt-3.5-turbo

    key players and their contributions in sports 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
     Brigham
    -0.55
     civilisation
    -0.54
    STATE
    -0.53
     âĢº
    -0.52
     Gaddafi
    -0.52
     inevitably
    -0.51
    billion
    -0.51
     ALWAYS
    -0.51
     Manifest
    -0.49
     Wilde
    -0.49
    POSITIVE LOGITS
     respectively
    0.87
     sidx
    0.78
     apiece
    0.77
     TBA
    0.75
    çĶ°
    0.71
    oother
    0.71
     actionGroup
    0.67
    luaj
    0.66
    emi
    0.65
     respective
    0.63
    Activations Density 1.362%

    No Known Activations