INDEX

Explanations

references 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 @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

enderror

-0.95

Życiorys

-0.94

 pitié

-0.81

sonaro

-0.79

 sauvages

-0.76

 Głów

-0.74

 Nagpur

-0.73

 sauvage

-0.73

 Svensk

-0.71

endphp

-0.71

POSITIVE LOGITS

 bridge

2.81

 bridges

2.80

 Bridge

2.65

Bridge

2.46

 BRIDGE

2.42

 Bridges

2.41

bridge

2.40

bridges

2.28

Bridges

2.27

 BRID

2.02

Activations Density 0.040%

references to bridges

No Comments

No Known Activations