© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 1349
    Prev
    Next
    INDEX
    Explanations

    business entities and organizations with a special focus on companies and specific terms

    oai_token-act-pair · gpt-3.5-turbo

    brand names and specific entities

    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
    iewicz
    -0.63
    icularly
    -0.60
    è£ħ
    -0.59
    ategory
    -0.58
     Pwr
    -0.56
    meet
    -0.56
    ottesville
    -0.56
    é¾įåĸļ士
    -0.54
    ember
    -0.54
    aples
    -0.54
    POSITIVE LOGITS
    iffs
    0.60
    ths
    0.57
     fortune
    0.56
    division
    0.55
    Ħ¢
    0.53
    µ
    0.52
    rac
    0.51
    stro
    0.50
     Ltd
    0.50
    aires
    0.48
    Activations Density 0.218%

    No Known Activations