© 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. 11-RES-JB
    11. 1074
    Prev
    Next
    INDEX
    Explanations

    pronouns and verbs related to work or progress

    oai_token-act-pair · gpt-3.5-turbo

    pronouns, particularly those referring to groups or individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IFIED
    -0.70
    اÙĦ
    -0.64
    inn
    -0.63
     Binding
    -0.59
     Ù
    -0.58
    aca
    -0.58
    Giving
    -0.57
    <?
    -0.57
     Ban
    -0.57
     ÙĪ
    -0.55
    POSITIVE LOGITS
     relate
    1.03
     relates
    0.95
     progresses
    0.93
     embark
    0.90
     prepares
    0.88
     transitions
    0.87
     transitioned
    0.87
     prepare
    0.86
     matured
    0.86
     traverse
    0.86
    Activations Density 0.077%

    No Known Activations