© 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. 9-RES-JB
    11. 16766
    Prev
    Next
    INDEX
    Explanations

    the word "Parents"

    oai_token-act-pair · gpt-3.5-turbo

    references to parents or parental figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Flavoring
    -0.79
     Kingdoms
    -0.77
     Antar
    -0.72
    atility
    -0.67
    paio
    -0.65
    ibaba
    -0.64
     sclerosis
    -0.64
     Britann
    -0.64
    jriwal
    -0.63
     Baldwin
    -0.62
    POSITIVE LOGITS
    hetical
    1.52
    hesis
    1.37
    hetically
    1.19
    heses
    1.13
    parents
    0.94
    hes
    0.90
    hood
    0.84
    Parents
    0.78
    father
    0.74
    parent
    0.70
    Activations Density 0.039%

    No Known Activations