Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 20419
    Prev
    Next
    INDEX
    Explanations

    email-related communication

    oai_token-act-pair · gpt-3.5-turbo

    references to email addresses and associated metadata

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Expand
    -0.83
     temples
    -0.70
     signage
    -0.69
    paces
    -0.67
    interstitial
    -0.65
     Inher
    -0.63
     Judges
    -0.63
     Flesh
    -0.61
     Underground
    -0.59
     Mud
    -0.59
    POSITIVE LOGITS
    olicited
    0.93
    onse
    0.85
     Abedin
    0.81
     UNCLASSIFIED
    0.76
     <[
    0.76
     cipher
    0.75
    Message
    0.75
    reply
    0.73
    >[
    0.72
     john
    0.70
    Activations Density 0.170%

    No Known Activations