INDEX

Explanations

phrases indicating physical distance or separation

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

 Kond

-0.74

ึ้น

-0.74

følgelig

-0.71

 Moseley

-0.68

cVar

-0.66

 modelAndView

-0.66

Παραπομπές

-0.66

parsedMessage

-0.65

zez

-0.65

katu

-0.65

POSITIVE LOGITS

away

1.06

 Away

1.04

Away

1.03

 away

0.97

 AWAY

0.90

AWAY

0.78

aways

0.69

EDEFAULT

0.67

 Svet

0.59

 Mero

0.59

Activations Density 0.063%

phrases indicating physical distance or separation

No Comments

No Known Activations