© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2-RES-JB
    11. 1008
    Prev
    Next
    INDEX
    Explanations

    the syllable "Tre"

    oai_token-act-pair · gpt-4-turbo

    names or terms related to the name "Trevor"

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Tre" or variations of it, indicating a focus on a specific person or character

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¡
    -0.75
    INESS
    -0.72
    enegger
    -0.72
     Kirin
    -0.72
     WORLD
    -0.68
     Parenthood
    -0.68
    anwhile
    -0.64
     Samoa
    -0.64
     Gujar
    -0.64
     incidentally
    -0.63
    POSITIVE LOGITS
    uner
    1.03
    asures
    0.99
    acher
    0.96
    rive
    0.95
    ngth
    0.92
    llo
    0.90
    anium
    0.90
    bil
    0.87
    rell
    0.87
    asury
    0.86
    Activations Density 0.004%

    No Known Activations