© 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 EvalsExportsinterp-engineNEWAPI 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. 21060
    Prev
    Next
    INDEX
    Explanations

    descriptions of fictional relationships or friendships

    oai_token-act-pair · gpt-3.5-turbo

    themes related to friendship and relationships between characters in narratives

    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
    âĹ¼
    -0.62
    zai
    -0.60
    ware
    -0.58
    ''.
    -0.58
    Advertisements
    -0.58
    SPONSORED
    -0.57
     Jackets
    -0.55
    )].
    -0.54
    ariat
    -0.53
    Constructed
    -0.53
    POSITIVE LOGITS
    cedented
    0.54
    dinand
    0.54
     decoding
    0.52
     practition
    0.51
     entreprene
    0.51
     volunte
    0.50
    DeliveryDate
    0.49
    upiter
    0.47
     surg
    0.47
    aditional
    0.47
    Activations Density 0.051%

    No Known Activations