INDEX

Explanations

statements of opinion or critique related to governance and policy issues

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 kadang

-0.63

 occasionally

-0.62

 Occasionally

-0.61

 Sometimes

-0.60

Sometimes

-0.60

 sometimes

-0.59

Portail

-0.59

 ibland

-0.58

sometimes

-0.57

 déterminé

-0.55

POSITIVE LOGITS

why

0.87

 neither

0.86

 seharusnya

0.85

 Зачем

0.81

 Shouldn

0.81

shame

0.79

Shouldn

0.79

 Shame

0.79

 shame

0.78

 taxpayers

0.78

Activations Density 0.451%

statements of opinion or critique related to governance and policy issues

No Comments

No Known Activations