© 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. 9-RES-JB
    11. 4616
    Prev
    Next
    INDEX
    Explanations

    phrases related to strong emotions and personal connections

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to falling in love

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ctive
    -0.74
    iliary
    -0.72
    shaw
    -0.65
    herty
    -0.63
    nea
    -0.63
    sylv
    -0.63
    200000
    -0.62
    wcs
    -0.62
    future
    -0.62
    CLA
    -0.62
    POSITIVE LOGITS
     deaf
    0.75
     asleep
    0.73
    emetery
    0.72
    ĺħ
    0.71
     Haku
    0.71
     Pieces
    0.69
     Pigs
    0.68
    alach
    0.66
    osate
    0.65
     trap
    0.64
    Activations Density 0.106%

    No Known Activations