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. 5-RES-JB
    6. 17940
    Prev
    Next
    INDEX
    Explanations

    action phrases indicating a call to action or subscription request

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to newsletter subscription actions

    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
     gone
    -0.70
    voy
    -0.67
    hur
    -0.66
     chilling
    -0.64
     omin
    -0.64
     stoked
    -0.64
    warning
    -0.64
     menacing
    -0.63
    ylum
    -0.63
    tymology
    -0.62
    POSITIVE LOGITS
    asty
    0.77
     receive
    0.73
    ilet
    0.70
     srfAttach
    0.68
     submit
    0.65
    ete
    0.65
    abeth
    0.64
     participate
    0.64
    asted
    0.64
     Baptist
    0.64
    Activations Density 0.124%

    No Known Activations