© 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. 841
    Prev
    Next
    INDEX
    Explanations

    instances where the word "thought" is used to express an opinion or consideration

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing thoughts or opinions about events or experiences

    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
    ãĤ´ãĥ³
    -0.86
    è¦ļéĨĴ
    -0.80
    adra
    -0.78
    ãĤ¬
    -0.78
     Nationwide
    -0.76
    ãĤº
    -0.75
    OURCE
    -0.73
     Regions
    -0.71
    FIG
    -0.65
    ãĥ©ãĥ³
    -0.64
    POSITIVE LOGITS
     might
    1.02
     sounded
    0.98
    'd
    0.96
    might
    0.90
     would
    0.84
     ought
    0.84
     deserved
    0.82
     invincible
    0.82
     resembled
    0.80
     joking
    0.79
    Activations Density 0.110%

    No Known Activations