© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 22193
    Prev
    Next
    INDEX
    Explanations

    phrases related to email subscriptions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to receiving information or offers

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

    No Comments

    Negative Logits
    pan
    -0.74
    sect
    -0.67
    markets
    -0.63
    sis
    -0.61
    fall
    -0.58
    uration
    -0.58
     Tsukuyomi
    -0.58
     Bengal
    -0.57
     illum
    -0.57
    erer
    -0.56
    POSITIVE LOGITS
    imentary
    0.88
     invitations
    0.84
     notifications
    0.84
    TING
    0.79
    olicited
    0.79
     notification
    0.76
    terson
    0.75
     acknowled
    0.75
    imental
    0.73
    ograp
    0.72
    Activations Density 0.022%

    No Known Activations