© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 18540
    Prev
    Next
    INDEX
    Explanations

    instances of the word "director" and related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals in director roles

    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
     Saga
    -0.63
    theless
    -0.61
    iths
    -0.61
     Sovere
    -0.58
    TON
    -0.57
    âĨij
    -0.56
     Fighters
    -0.55
    adesh
    -0.52
    Leader
    -0.52
     silicone
    -0.52
    POSITIVE LOGITS
    ial
    1.15
    ates
    1.09
    general
    1.06
    ate
    1.06
     general
    0.94
    ials
    0.90
    ovie
    0.89
    ially
    0.85
    iate
    0.81
    atus
    0.78
    Activations Density 0.050%

    No Known Activations