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. 9-RES-JB
    6. 12895
    Prev
    Next
    INDEX
    Explanations

    phrases related to receiving emails and offers

    oai_token-act-pair · gpt-3.5-turbo

    phrases involving agreements to receive updates and offers

    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
    stood
    -0.71
    pex
    -0.69
     Eug
    -0.63
    cious
    -0.62
    Registered
    -0.61
    wolf
    -0.59
    ufact
    -0.58
    abase
    -0.58
    lein
    -0.57
    mens
    -0.56
    POSITIVE LOGITS
     promotions
    1.04
     notifications
    0.89
    ivals
    0.81
     invitations
    0.80
     subscriptions
    0.78
     previews
    0.78
    Privacy
    0.75
     warranties
    0.72
     attachments
    0.71
     updates
    0.71
    Activations Density 0.040%

    No Known Activations