© 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 EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 9946
    Prev
    Next
    INDEX
    Explanations

    email timestamps and related email content

    oai_token-act-pair · gpt-3.5-turbo

    structured email metadata information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     temples
    -0.89
    aepernick
    -0.76
     Furious
    -0.71
     meter
    -0.67
     rhy
    -0.65
     premie
    -0.64
     Tsukuyomi
    -0.63
     joints
    -0.63
     infographic
    -0.63
     Kard
    -0.62
    POSITIVE LOGITS
    olicited
    1.10
     Abedin
    0.94
    afort
    0.91
     Received
    0.80
    mail
    0.80
    Guest
    0.79
     forwarded
    0.78
    Mail
    0.77
    Message
    0.77
     NOTICE
    0.76
    Activations Density 0.124%

    No Known Activations