© 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. 8-RES-JB
    11. 2434
    Prev
    Next
    INDEX
    Explanations

    different types or varieties of items

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating different types or categories of subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    esses
    -0.85
    ĸļ
    -0.74
    oult
    -0.74
     lest
    -0.73
    ellen
    -0.71
    lund
    -0.70
    Clar
    -0.70
     Below
    -0.68
    erves
    -0.68
    eks
    -0.68
    POSITIVE LOGITS
     equipment
    0.82
     clothing
    0.82
     person
    0.81
     intermediate
    0.78
     medicine
    0.78
     activity
    0.78
     weaponry
    0.78
     measurement
    0.77
     crossover
    0.76
     manif
    0.76
    Activations Density 0.076%

    No Known Activations