© 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. 12055
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal opinions or beliefs

    oai_token-act-pair · gpt-3.5-turbo
    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
    accompan
    -0.69
    ãĥ©ãĥ³
    -0.69
     unsus
    -0.67
    odge
    -0.66
    everal
    -0.64
    azar
    -0.63
    ugi
    -0.59
     redes
    -0.58
    figured
    -0.58
    earchers
    -0.58
    POSITIVE LOGITS
     anymore
    2.15
     nor
    1.44
     whatsoever
    1.41
    nor
    1.15
     anyway
    1.10
     unless
    1.10
     anyways
    1.09
    yet
    1.06
     slightest
    1.04
     anywhere
    1.02
    Activations Density 0.458%

    No Known Activations