INDEX

Explanations

sections of text containing legal or procedural terminology, particularly those indicating judgments or rulings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

ed

-1.03

 تضيفلها

-0.87

 Pank

-0.81

InputBorder

-0.78

 Newberry

-0.76

Kw

-0.76

 Tick

-0.75

 Eddy

-0.75

 TICK

-0.74

Tikang

-0.71

POSITIVE LOGITS

↵↵↵

2.05

↵↵↵↵

1.36

↵↵↵↵↵↵

1.19

↵↵↵↵↵

1.17

↵↵↵↵↵↵↵

1.14

↵↵↵↵↵↵↵↵↵

0.99

↵↵↵↵↵↵↵↵

0.98

↵↵↵↵↵↵↵↵↵↵↵

0.98

);

0.94

↵↵↵↵↵↵↵↵↵↵↵↵

0.93

Activations Density 0.167%

sections of text containing legal or procedural terminology, particularly those indicating judgments or rulings

No Comments

No Known Activations