INDEX

Explanations

references to lakes or related geographical features

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

"Lake"

np_acts-logits-general · gemini-2.0-flash

names of lakes

np_acts-logits-general · gemini-2.5-flash-lite

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

 Monfieur

-0.96

 myſelf

-0.92

 greateſt

-0.86

 ſeveral

-0.83

 Jefus

-0.82

 Anſ

-0.80

 Theſe

-0.77

 poffible

-0.75

 reaſon

-0.75

 itſelf

-0.74

POSITIVE LOGITS

Lakes

0.72

 Lakes

0.72

 lakes

0.70

 Lake

0.69

lakes

0.65

 lake

0.61

Lake

0.57

TypedDataSet

0.56

 resourceCulture

0.50

 Lakers

0.50

Activations Density 0.055%

references to lakes or related geographical features

"Lake"

names of lakes

No Comments

No Known Activations