© 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. 17064
    Prev
    Next
    INDEX
    Explanations

    specific references to a location or entity named "Pop"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "Pop" in various contexts

    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
    BILITIES
    -0.72
     pleasure
    -0.69
    ĵĺ
    -0.68
    RAW
    -0.67
    actionDate
    -0.66
     legs
    -0.66
     Monstrous
    -0.65
     diplom
    -0.65
     dishonest
    -0.64
    perse
    -0.64
    POSITIVE LOGITS
    Pop
    1.11
    ular
    1.09
    ularity
    1.09
    corn
    1.09
    ulations
    1.07
    ulus
    0.95
    ulated
    0.89
    ulates
    0.89
    ulate
    0.88
     Pop
    0.87
    Activations Density 0.004%

    No Known Activations