© 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. 1-RES-JB
    11. 6685
    Prev
    Next
    INDEX
    Explanations

    mentions of "parents"

    oai_token-act-pair · gpt-3.5-turbo

    references to parental figures and their influence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Flavoring
    -0.67
    ACTED
    -0.63
     sclerosis
    -0.63
     HRC
    -0.62
    atility
    -0.62
    swing
    -0.62
     JFK
    -0.61
    CONT
    -0.61
     stroke
    -0.60
    psey
    -0.59
    POSITIVE LOGITS
    parents
    1.12
    hetical
    1.12
    hesis
    1.07
    Parents
    1.02
     Parents
    0.95
    hetically
    0.94
    heses
    0.92
     parents
    0.92
    chool
    0.79
    father
    0.79
    Activations Density 0.017%

    No Known Activations