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. 1-RES-JB
    6. 19161
    Prev
    Next
    INDEX
    Explanations

    words related to discipline or punishment

    oai_token-act-pair · gpt-3.5-turbo

    verbs related to the concept of dining or eating experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    channelAvailability
    -0.65
    chie
    -0.64
     channel
    -0.62
    atically
    -0.61
     bet
    -0.61
    soDeliveryDate
    -0.61
    DOC
    -0.60
    osponsors
    -0.60
     earthqu
    -0.60
     welcome
    -0.60
    POSITIVE LOGITS
    ining
    1.38
    ined
    1.35
    iners
    0.99
    iner
    0.81
    inery
    0.79
     largeDownload
    0.79
    ĸļ
    0.78
     tong
    0.78
    uania
    0.76
    redients
    0.76
    Activations Density 0.011%

    No Known Activations