© 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. 10167
    Prev
    Next
    INDEX
    Explanations

    phrases related to feedback and critique

    oai_token-act-pair · gpt-3.5-turbo

    statements expressing uncertainty or imperfection

    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
    ¥ŀ
    -0.58
    ãĥ©ãĥ³
    -0.56
    veyard
    -0.55
    arthy
    -0.54
    èĢ
    -0.54
     ensured
    -0.54
    pired
    -0.54
    ushi
    -0.53
    appropriately
    -0.52
     unim
    -0.52
    POSITIVE LOGITS
     anymore
    1.45
     nor
    1.35
     but
    1.24
     tho
    1.19
    nor
    1.13
     though
    1.09
     BUT
    1.09
    yet
    1.02
    but
    0.96
    But
    0.92
    Activations Density 0.660%

    No Known Activations