© 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. 10087
    Prev
    Next
    INDEX
    Explanations

    terms related to magnetic fields and electrical current

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with magnetic and electrical phenomena

    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
    lain
    -0.90
    tower
    -0.85
    hov
    -0.84
    ortium
    -0.82
    igun
    -0.82
    imately
    -0.82
    naire
    -0.80
    lr
    -0.80
    nered
    -0.79
    alos
    -0.76
    POSITIVE LOGITS
     anomalies
    1.02
     significance
    1.01
     activity
    1.00
     disturbances
    0.93
     properties
    0.92
     distress
    0.92
     stimulation
    0.91
    ized
    0.90
     prowess
    0.89
     associations
    0.88
    Activations Density 0.149%

    No Known Activations