© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 12-RES-JB
    11. 4062
    Prev
    Next
    INDEX
    Explanations

    narrative details about a personal experience, particularly involving emotional moments and interactions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    emotional expressions related to loss and grief

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ñ
    -1.03
    ò
    -0.99
    ¥ŀ
    -0.96
    ãĥīãĥ©
    -0.95
    defense
    -0.94
    avored
    -0.93
    ospons
    -0.91
    ãĤ´ãĥ³
    -0.90
     srf
    -0.90
    heast
    -0.90
    POSITIVE LOGITS
     paed
    1.48
     realise
    1.43
     realised
    1.43
     mum
    1.42
     rubbish
    1.42
    ',"
    1.40
     maths
    1.36
     apologised
    1.34
     £
    1.32
     colour
    1.32
    Activations Density 1.027%

    No Known Activations