© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 7834
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to a specific person

    oai_token-act-pair · gpt-3.5-turbo

    the name "Ashraf."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bunny
    -0.65
     stem
    -0.63
     altern
    -0.61
     invention
    -0.60
     Script
    -0.60
     Whale
    -0.59
     creation
    -0.59
     anticipation
    -0.59
     override
    -0.59
     headset
    -0.59
    POSITIVE LOGITS
    raf
    4.78
    raph
    1.34
    ra
    1.24
    rab
    1.16
    raq
    1.12
    ram
    1.10
    raft
    1.09
    rov
    1.06
    rip
    1.05
    ras
    1.04
    Activations Density 0.016%

    No Known Activations