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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3-RES-JB
    11. 22570
    Prev
    Next
    INDEX
    Explanations

    email-related terms, particularly focusing on Gmail

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Gmail service

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    semble
    -0.81
    SPONSORED
    -0.77
    nings
    -0.74
    66666666
    -0.73
    hani
    -0.71
    Jere
    -0.71
    stood
    -0.68
    lined
    -0.67
    zynski
    -0.67
    ivism
    -0.66
    POSITIVE LOGITS
     Gmail
    1.10
     inbox
    0.99
     Pavilion
    0.83
     username
    0.76
     Keyboard
    0.75
     Suite
    0.73
    awei
    0.73
    geist
    0.72
    email
    0.71
    imei
    0.70
    Activations Density 0.012%

    No Known Activations