© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 12822
    Prev
    Next
    INDEX
    Explanations

    mentions of relationships between individuals

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating relationships and connections between people

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    è£ħ
    -0.66
     Marketable
    -0.64
     exting
    -0.60
    Ranked
    -0.59
    ãĤ¦ãĤ¹
    -0.59
    ãĥīãĥ©
    -0.59
    ashington
    -0.58
    çļĦ
    -0.58
     conduc
    -0.57
     WATCHED
    -0.56
    POSITIVE LOGITS
     I
    1.89
     we
    1.31
     me
    1.27
    I
    1.22
     my
    1.19
     i
    1.17
     mine
    1.04
     myself
    0.88
     My
    0.87
     We
    0.84
    Activations Density 0.517%

    No Known Activations