INDEX

Explanations

the German word "für," which means "for," and related terms indicating purpose or significance

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

vol

-0.73

Vol

-0.71

Vol

-0.66

vol

-0.65

 Dawes

-0.63

 navideñas

-0.60

 Scopus

-0.60

 urbanos

-0.59

 McFar

-0.57

!*\

-0.57

POSITIVE LOGITS

 für

1.54

 Für

1.12

Für

1.11

für

1.07

 FÜR

1.02

dla

0.93

 voor

0.88

ofür

0.88

Voor

0.85

 VOOR

0.84

Activations Density 0.043%

the German word "für," which means "for," and related terms indicating purpose or significance

No Comments

No Known Activations