© 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. 11-RES-JB
    11. 7022
    Prev
    Next
    INDEX
    Explanations

    email-related phrases indicating delivery to an inbox

    oai_token-act-pair · gpt-3.5-turbo

    references to email subscriptions and inbox deliveries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aft
    -0.70
    rers
    -0.68
    gling
    -0.67
     Patriarch
    -0.64
    bach
    -0.63
     Kard
    -0.60
    urat
    -0.58
     wik
    -0.57
    arks
    -0.56
    gat
    -0.55
    POSITIVE LOGITS
     Subscribe
    0.98
     inbox
    0.72
    ategor
    0.69
    ãĤ¯
    0.69
     weekday
    0.64
    ombat
    0.64
     mailbox
    0.63
     Email
    0.62
    helle
    0.62
    hello
    0.61
    Activations Density 0.026%

    No Known Activations