© 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 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. 16634
    Prev
    Next
    INDEX
    Explanations

    words related to individuals recounting their experiences of growing up

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "grew up" and its variations indicating childhood 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
    rium
    -0.83
    asus
    -0.82
    İĭ
    -0.72
    idon
    -0.69
    apo
    -0.67
    assian
    -0.65
    ongyang
    -0.64
    vernment
    -0.64
    berus
    -0.64
    ancial
    -0.64
    POSITIVE LOGITS
     surrounded
    0.98
     idol
    0.97
     believing
    0.93
     hating
    0.87
     watching
    0.85
     immersed
    0.83
    chool
    0.83
     listening
    0.82
     dreaming
    0.80
     playing
    0.78
    Activations Density 0.039%

    No Known Activations