INDEX

Explanations

references to bridges and their various contexts

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

bridges

np_acts-logits-general · gemini-2.0-flash

bridge, connections, circuits

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Svensk

-0.78

 sauvages

-0.76

Ino

-0.76

roslav

-0.75

 elettrico

-0.73

 vatt

-0.70

;*/

-0.67

 Sligo

-0.66

 Рабо

-0.66

 McIntosh

-0.65

POSITIVE LOGITS

 bridges

1.27

 bridge

1.24

 Bridge

1.21

 Bridges

1.16

 BRIDGE

1.15

Bridges

1.12

Bridge

1.08

bridge

1.04

bridges

1.01

 BRID

0.94

Activations Density 0.270%

references to bridges and their various contexts

bridges

bridge, connections, circuits

No Comments

No Known Activations