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. 20235
    Prev
    Next
    INDEX
    Explanations

    phrases or words that have the letter 'y' followed by a high intensity, emotional word

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 'y'

    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
     Wonderland
    -0.77
     Painter
    -0.69
    ãĥ¼ãĥĨãĤ£
    -0.69
     Examiner
    -0.67
    tenance
    -0.66
    ãĥ´ãĤ¡
    -0.65
     Trilogy
    -0.64
    Oracle
    -0.64
    éĹĺ
    -0.64
    FactoryReloaded
    -0.63
    POSITIVE LOGITS
    ahoo
    1.07
    idd
    0.95
    orkshire
    0.94
    anked
    0.90
    ummy
    0.89
    ield
    0.88
    aku
    0.86
    anking
    0.86
    umen
    0.85
    outh
    0.84
    Activations Density 0.024%

    No Known Activations