© 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. 10-RES-JB
    11. 5131
    Prev
    Next
    INDEX
    Explanations

    phrases introducing information or updates

    oai_token-act-pair · gpt-3.5-turbo

    phrases that introduce information or summaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ename
    -0.77
    enegger
    -0.69
    ifice
    -0.65
    psc
    -0.61
    clerosis
    -0.61
    strength
    -0.61
    aukee
    -0.61
    cler
    -0.60
     slightest
    -0.60
    inent
    -0.59
    POSITIVE LOGITS
     happened
    1.27
     happens
    1.21
     transpired
    1.12
     else
    1.03
     happ
    0.95
     awaits
    0.89
     ensued
    0.89
     Happ
    0.89
     we
    0.86
     you
    0.86
    Activations Density 0.067%

    No Known Activations