© 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. 9-RES-JB
    11. 15529
    Prev
    Next
    INDEX
    Explanations

    pronouns and verbs related to seeking information or understanding

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "We" or its variations, indicating a focus on collective actions or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    forms
    -0.68
     Haku
    -0.61
     guiActiveUnfocused
    -0.59
     decoration
    -0.58
    ãĤ³
    -0.57
    Application
    -0.56
     fluids
    -0.56
     flows
    -0.56
    MY
    -0.56
    andon
    -0.56
    POSITIVE LOGITS
    akening
    1.08
    athered
    1.05
    ibo
    1.01
    've
    0.99
    asel
    0.99
    blogs
    0.98
     wondered
    0.97
    ighed
    0.97
    igh
    0.95
    'll
    0.94
    Activations Density 0.188%

    No Known Activations