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. 8-RES-JB
    6. 21021
    Prev
    Next
    INDEX
    Explanations

    emotional reactions, specifically crying

    oai_token-act-pair · gpt-3.5-turbo

    instances of emotional responses, particularly related to crying

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    DragonMagazine
    -0.91
    ipment
    -0.78
    topic
    -0.72
    å§«
    -0.71
    ainment
    -0.71
    jiang
    -0.69
    available
    -0.66
    rupulous
    -0.65
    ugal
    -0.65
    BLIC
    -0.64
    POSITIVE LOGITS
     loudly
    1.29
     uncontroll
    1.19
     aloud
    1.18
     silently
    1.08
     bitterly
    1.06
     furiously
    1.06
     violently
    1.02
     passionately
    1.01
     horribly
    0.98
     angrily
    0.98
    Activations Density 0.175%

    No Known Activations