INDEX

Explanations

concepts related to legal proceedings and frameworks

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

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

")->

-0.76

')->

-0.73

 pihaknya

-0.70

이다

-0.60

だろうか

-0.59

のだろうか

-0.58

herself

-0.57

ようだ

-0.56

だが

-0.55

())->

-0.55

POSITIVE LOGITS

you

3.04

 your

2.97

your

2.48

you

2.15

Your

2.06

 Your

1.94

 yourself

1.89

 YOUR

1.87

 yours

1.86

You

1.79

Activations Density 2.302%

concepts related to legal proceedings and frameworks

No Comments

No Known Activations