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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 22597
    Prev
    Next
    INDEX
    Explanations

    information about people's relationships, such as marriages, children, and spouses

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to family dynamics and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
    rack
    -0.79
    ommel
    -0.76
     takedown
    -0.74
    ube
    -0.73
    peak
    -0.72
     captcha
    -0.69
     LEVEL
    -0.68
    lies
    -0.68
    ĸļ
    -0.67
    forcement
    -0.67
    POSITIVE LOGITS
     divorced
    1.40
     daughters
    1.34
     divor
    1.29
     divorce
    1.23
     daughter
    1.22
     sons
    1.11
     granddaughter
    1.10
     grandchildren
    1.09
     children
    1.04
     eldest
    1.04
    Activations Density 0.296%

    No Known Activations