© 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. 15736
    Prev
    Next
    INDEX
    Explanations

    email-related fields and prompts

    oai_token-act-pair · gpt-3.5-turbo

    instances of email validation phrases

    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
    guided
    -0.62
    pent
    -0.61
     barg
    -0.61
     bargain
    -0.60
    trak
    -0.60
    nces
    -0.59
    terday
    -0.58
    inav
    -0.56
    itism
    -0.55
     NRS
    -0.54
    POSITIVE LOGITS
     pestic
    0.63
     UNCLASSIFIED
    0.61
    Companies
    0.60
    ornia
    0.59
    uckles
    0.58
     separatists
    0.57
     Quin
    0.56
     Cookies
    0.55
     Reboot
    0.55
    ittal
    0.54
    Activations Density 0.050%

    No Known Activations