INDEX

Explanations

phrases that indicate titles or names, especially those formatted with quotes and parentheses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

iſh

-0.51

Nevertheless

-0.50

phazard

-0.48

 MessageBoxIcon

-0.48

iſ

-0.47

 trygg

-0.47

 uovo

-0.47

ïa

-0.47

 entanto

-0.46

 cipolla

-0.46

POSITIVE LOGITS

 Roskov

0.83

IntoConstraints

0.81

SpringBootTest

0.68

 ImportError

0.64

 GenerationType

0.63

>{@

0.62

 Walkover

0.60

 <=",

0.60

tomans

0.59

adaptiveStyles

0.59

Activations Density 0.367%

phrases that indicate titles or names, especially those formatted with quotes and parentheses

No Comments

No Known Activations