© 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. 6390
    Prev
    Next
    INDEX
    Explanations

    phrases related to love and friendship

    oai_token-act-pair · gpt-3.5-turbo

    the concept of love and friendship in various contexts

    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
    •layer 11 - love

    No Comments

    Negative Logits
     Unch
    -0.66
    Reviewer
    -0.66
     Outbreak
    -0.64
    aghd
    -0.63
    itone
    -0.63
     PHOTO
    -0.59
     Homo
    -0.58
    ILLE
    -0.58
    outside
    -0.58
    >>
    -0.58
    POSITIVE LOGITS
    rage
    0.77
    hate
    0.76
     daddy
    0.74
    college
    0.74
    bitious
    0.72
     affection
    0.67
    anamo
    0.66
    rust
    0.65
     lust
    0.65
     conserve
    0.65
    Activations Density 0.142%

    No Known Activations