© 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. 3-RES-JB
    6. 15462
    Prev
    Next
    INDEX
    Explanations

    greetings or mentions of specific locations like "Romeo."

    oai_token-act-pair · gpt-3.5-turbo

    the word "hello" with varying frequencies and references to the character Romeo

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gow
    -0.76
    orne
    -0.75
    ible
    -0.73
    lin
    -0.73
    shaw
    -0.70
    atch
    -0.70
    wer
    -0.69
    otin
    -0.68
    pter
    -0.67
    ener
    -0.67
    POSITIVE LOGITS
     Samoa
    0.77
     Marino
    0.76
    ÄŁ
    0.72
     Lucia
    0.71
     IMAGES
    0.70
    etheless
    0.69
    REDACTED
    0.67
     CTR
    0.67
    INO
    0.66
     Tale
    0.64
    Activations Density 0.028%

    No Known Activations