© 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. 1-RES-JB
    11. 3415
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Vale."

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically character names and place names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    detail
    -0.76
    itsch
    -0.74
    aton
    -0.73
    iday
    -0.73
    iour
    -0.72
    Indiana
    -0.71
    iasis
    -0.69
    itional
    -0.69
    aquin
    -0.68
    stroke
    -0.67
    POSITIVE LOGITS
     Beacon
    1.04
     Grimm
    0.98
     RW
    0.96
     Vale
    0.95
    BY
    0.88
     Pyrrha
    0.88
     Catalyst
    0.87
     Emerald
    0.85
     Coil
    0.84
     Valkyrie
    0.83
    Activations Density 0.023%

    No Known Activations