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

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 15151
    Prev
    Next
    INDEX
    Explanations

    references to sending or receiving information via email or physical mail

    oai_token-act-pair · gpt-3.5-turbo

    references to mailing lists and mailing-related activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    obal
    -0.72
    eva
    -0.71
    ellen
    -0.70
    imposed
    -0.70
    nov
    -0.70
    Ti
    -0.68
    mobi
    -0.68
    oti
    -0.68
    neutral
    -0.66
    200000
    -0.66
    POSITIVE LOGITS
     mailing
    1.16
     mail
    1.03
     mosqu
    0.96
     address
    0.91
     mailed
    0.82
     addresses
    0.80
     receipts
    0.80
     straw
    0.79
     inbox
    0.79
    legram
    0.79
    Activations Density 0.003%

    No Known Activations