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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 16323
    Prev
    Next
    INDEX
    Explanations

    mentions of crying or related emotions

    oai_token-act-pair · gpt-3.5-turbo

    instances of crying or expressions of emotional distress

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    efficients
    -0.72
    ajo
    -0.71
    ammy
    -0.71
     prescribe
    -0.69
    ratulations
    -0.68
    awaru
    -0.68
    velength
    -0.67
    ugal
    -0.67
    folios
    -0.67
    raviolet
    -0.66
    POSITIVE LOGITS
    baby
    0.98
    stals
    0.92
    ogen
    0.84
     cry
    0.84
     aloud
    0.82
    tags
    0.80
    stal
    0.80
    sis
    0.79
     crying
    0.79
     loudly
    0.78
    Activations Density 0.012%

    No Known Activations