© 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. 9-RES-JB
    11. 15589
    Prev
    Next
    INDEX
    Explanations

    names of individuals, likely in a news or sports context

    oai_token-act-pair · gpt-3.5-turbo

    phrases that contain a variety of suffixes or endings, indicating a focus on morphological variations of words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     capit
    -0.70
     ($)
    -0.70
    cape
    -0.62
    Downloadha
    -0.58
    thodox
    -0.58
    nexus
    -0.57
    maxwell
    -0.56
     vulner
    -0.55
     reckoning
    -0.55
    Ô
    -0.55
    POSITIVE LOGITS
    essor
    0.79
    uve
    0.74
    ardo
    0.73
    estern
    0.71
    ornia
    0.70
    ixt
    0.70
     Ramos
    0.69
    rama
    0.69
     Phelps
    0.69
    ario
    0.67
    Activations Density 0.300%

    No Known Activations