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. 1591
    Prev
    Next
    INDEX
    Explanations

    phrases related to receiving information via email

    oai_token-act-pair · gpt-3.5-turbo

    references to email and inbox management

    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
     Parks
    -0.86
     skiing
    -0.79
     Corpor
    -0.76
    ARK
    -0.73
     MLG
    -0.66
     CSI
    -0.63
    arks
    -0.63
     ASA
    -0.63
    ETA
    -0.62
     Ski
    -0.62
    POSITIVE LOGITS
     inbox
    1.56
    ername
    1.02
    email
    0.96
    arella
    0.89
     mailbox
    0.88
    inia
    0.87
     Dragonbound
    0.87
    romeda
    0.84
    mail
    0.82
    acy
    0.82
    Activations Density 0.007%

    No Known Activations