INDEX

Explanations

references to individuals involved in various activities or processes

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

 elimin

-0.69

 establishment

-0.66

 creation

-0.65

 selection

-0.61

 formation

-0.61

 Establishment

-0.60

 removal

-0.59

 arrival

-0.59

 Creation

-0.58

 presence

-0.58

POSITIVE LOGITS

Rüyada

0.72

 Successfully

0.69

 BoxDecoration

0.69

 AppCompatTheme

0.69

Successfully

0.68

successfully

0.68

ynchronously

0.66

出版年

0.65

 efectivamente

0.64

 respectivamente

0.64

Activations Density 0.793%

references to individuals involved in various activities or processes

No Comments

No Known Activations