© 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. 3257
    Prev
    Next
    INDEX
    Explanations

    narratives about personal relationships and life events involving various individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to personal relationships and connections

    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
    earchers
    -0.77
    herer
    -0.69
     superflu
    -0.68
    lesi
    -0.68
     cutoff
    -0.67
    jriwal
    -0.66
    alions
    -0.64
    uge
    -0.63
     incompet
    -0.63
    cience
    -0.63
    POSITIVE LOGITS
     mutual
    1.38
     friendship
    1.36
     mutually
    1.22
     exchanging
    1.13
    relations
    1.11
     together
    1.10
    CHAT
    1.10
    Relations
    1.09
     rapport
    1.08
     relationship
    1.07
    Activations Density 0.736%

    No Known Activations