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. 10386
    Prev
    Next
    INDEX
    Explanations

    phrases related to recreational activities and events

    oai_token-act-pair · gpt-3.5-turbo

    gerunds and participles, particularly those ending in "ing"

    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
    Not in Any Lists

    No Comments

    Negative Logits
    bal
    -0.71
    peria
    -0.65
    pora
    -0.63
    omet
    -0.63
    trak
    -0.59
    ulet
    -0.59
    Ô
    -0.59
     defining
    -0.58
     Choose
    -0.57
    fitting
    -0.57
    POSITIVE LOGITS
    redients
    1.06
    tons
    0.93
    HAM
    0.88
     noises
    0.79
    ham
    0.74
     aids
    0.72
     havoc
    0.72
    ulate
    0.71
    lass
    0.70
     machines
    0.69
    Activations Density 0.177%

    No Known Activations