© 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. 18576
    Prev
    Next
    INDEX
    Explanations

    action verbs in the past tense specifically related to personal experiences

    oai_token-act-pair · gpt-3.5-turbo

    significant actions and events involving personal experiences and interactions

    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
    ©¶æ¥µ
    -0.91
    è£ħ
    -0.76
    ļé
    -0.75
     exting
    -0.73
    ulators
    -0.72
    £ı
    -0.71
    ãĤ¢ãĥ«
    -0.70
    å°Ĩ
    -0.67
    è¦ļéĨĴ
    -0.66
    clair
    -0.66
    POSITIVE LOGITS
     me
    2.55
     us
    2.37
     ME
    1.36
     Us
    1.28
     ours
    1.26
    me
    1.25
     Me
    1.20
     mine
    1.15
    Me
    1.08
     my
    0.96
    Activations Density 1.262%

    No Known Activations