Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 16022
    Prev
    Next
    INDEX
    Explanations

    phrases related to different aspects of love

    oai_token-act-pair · gpt-3.5-turbo

    themes and expressions related to love in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •layer 6 - love

    No Comments

    Negative Logits
    ħĭ
    -0.89
    soDeliveryDate
    -0.76
    */(
    -0.71
    icho
    -0.71
    ulhu
    -0.68
    Newsletter
    -0.68
    ocument
    -0.67
    ozo
    -0.64
     deviations
    -0.63
    imester
    -0.63
    POSITIVE LOGITS
    rix
    0.76
    thood
    0.76
     dearly
    0.75
     solitude
    0.72
    aukee
    0.69
    kind
    0.68
     âĿ
    0.68
     Samoa
    0.67
     Brune
    0.66
    birds
    0.66
    Activations Density 0.157%

    No Known Activations