© 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. 9899
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific or technical subjects, particularly focusing on specific biological or physical terms

    oai_token-act-pair · gpt-3.5-turbo

    words and terms related to scientific and biological characteristics or classifications

    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
    cedented
    -0.90
    bsite
    -0.80
    MED
    -0.76
    ortium
    -0.76
    foreseen
    -0.75
    Stats
    -0.74
    bourg
    -0.73
    soDeliveryDate
    -0.73
    effective
    -0.71
    Boss
    -0.70
    POSITIVE LOGITS
    ities
    1.12
    ity
    1.09
     tendencies
    1.08
    ism
    1.04
     phenomena
    0.98
    ization
    0.96
     activity
    0.96
     lifestyles
    0.94
     properties
    0.92
     structures
    0.91
    Activations Density 0.225%

    No Known Activations