INDEX

Explanations

references to physical structures or concepts related to "bridges."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 quæ

-0.76

 ejus

-0.73

lső

-0.61

 zufolge

-0.60

 doubtnut

-0.60

 habet

-0.59

 whoſe

-0.57

ulmuş

-0.57

,:);

-0.57

clerview

-0.57

POSITIVE LOGITS

bridge

1.06

 bridge

1.01

BRIDGE

0.92

 Bridge

0.90

Bridge

0.89

 bridges

0.87

 BRIDGE

0.85

 course

0.78

 ModelExpression

0.76

 Bridges

0.72

Activations Density 0.095%

references to physical structures or concepts related to "bridges."

No Comments

No Known Activations