© 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. 1318
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Santander" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Sant."

    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
    head
    -0.78
     sight
    -0.75
    heads
    -0.72
    HEAD
    -0.68
     departure
    -0.67
    aston
    -0.62
    LEASE
    -0.60
    KS
    -0.59
    ··
    -0.59
     Spit
    -0.57
    POSITIVE LOGITS
    oro
    1.02
    ega
    1.00
    illi
    1.00
    oku
    0.96
    esian
    0.95
    onica
    0.91
    oso
    0.90
    angelo
    0.89
    gage
    0.88
    onym
    0.88
    Activations Density 0.029%

    No Known Activations