© 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. 10-RES-JB
    11. 7457
    Prev
    Next
    INDEX
    Explanations

    Korean names or terms

    oai_token-act-pair · gpt-3.5-turbo

    names of specific individuals, particularly in a Korean context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    20439
    -0.77
    Italy
    -0.77
    ichick
    -0.75
    aukee
    -0.70
    iances
    -0.69
    Italian
    -0.67
    Generic
    -0.66
    lehem
    -0.65
    agna
    -0.64
    Introduced
    -0.63
    POSITIVE LOGITS
     Choi
    1.41
     Jae
    1.26
     Sung
    1.25
     Chung
    1.24
     Yong
    1.24
     Jung
    1.24
     Jong
    1.23
     Jin
    1.19
    jin
    1.19
    jong
    1.18
    Activations Density 0.080%

    No Known Activations