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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 9-RES-JB
    6. 770
    Prev
    Next
    INDEX
    Explanations

    phrases related to people coming in to take action

    oai_token-act-pair · gpt-3.5-turbo

    instances of coordination or connection between actions or subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ictions
    -0.73
    chance
    -0.62
    ansk
    -0.60
     centr
    -0.60
     Nept
    -0.58
    ongo
    -0.57
    acci
    -0.57
    ung
    -0.56
    altern
    -0.56
    until
    -0.56
    POSITIVE LOGITS
     wre
    0.95
     greet
    0.86
     greeted
    0.80
     greets
    0.79
     bite
    0.71
     slay
    0.69
     demanded
    0.68
     apologized
    0.67
     promptly
    0.67
    ocide
    0.66
    Activations Density 0.244%

    No Known Activations