© 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. 8-RES-JB
    11. 12931
    Prev
    Next
    INDEX
    Explanations

    personal relationships and connections

    oai_token-act-pair · gpt-3.5-turbo

    references to personal relationships and connections

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     itself
    -0.82
     compounded
    -0.70
    ulo
    -0.69
     Manufact
    -0.67
     simultaneous
    -0.64
     ratification
    -0.62
     dictated
    -0.61
    ensibly
    -0.60
     simulated
    -0.60
     SECTION
    -0.60
    POSITIVE LOGITS
     whom
    0.91
    ukemia
    0.83
     affection
    0.80
    imity
    0.76
    onym
    0.75
     admire
    0.75
     surn
    0.73
     acquaintance
    0.72
    irlf
    0.72
     acquaintances
    0.72
    Activations Density 0.281%

    No Known Activations