© 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. 2-RES-JB
    11. 9397
    Prev
    Next
    INDEX
    Explanations

    references to emails, particularly in a political context

    oai_token-act-pair · gpt-3.5-turbo

    mentions of emails related to Hillary Clinton

    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
    OV
    -0.80
     Raleigh
    -0.73
     Durham
    -0.71
    scope
    -0.69
    Jer
    -0.69
     Glasgow
    -0.68
     Sul
    -0.67
    045
    -0.66
    GBT
    -0.66
    TRY
    -0.65
    POSITIVE LOGITS
     emails
    1.12
     Emails
    1.12
     inbox
    1.03
     newsletters
    0.95
     messages
    0.91
    mails
    0.89
     correspondence
    0.87
    email
    0.87
     dumps
    0.84
     email
    0.83
    Activations Density 0.017%

    No Known Activations