© 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. 2341
    Prev
    Next
    INDEX
    Explanations

    people's names starting with "Ped"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Ped" and its variations in different contexts

    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
     furnace
    -0.69
     freezes
    -0.69
    uries
    -0.67
     hangar
    -0.67
     forge
    -0.65
     Firefly
    -0.65
     DRAGON
    -0.65
     Avatar
    -0.65
     Void
    -0.63
     AWS
    -0.63
    POSITIVE LOGITS
     Ped
    3.64
    Ped
    3.34
     ped
    2.99
     paed
    2.00
    ped
    1.99
     pedal
    1.64
     pedoph
    1.63
     pedals
    1.49
     Pediatrics
    1.48
     pediatric
    1.42
    Activations Density 0.021%

    No Known Activations