INDEX

Explanations

negations and expressions related to absence or unavailability

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/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.8.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

Spoljašnje

-0.76

tzmann

-0.70

 bezeichneter

-0.69

 lenker

-0.68

 Hadrian

-0.66

 kuan

-0.61

 нему

-0.61

 GreatSchools

-0.60

 للاسماء

-0.60

-0.56

POSITIVE LOGITS

 ใน

1.00

 في

1.00

 وفي

0.98

 midst

0.96

Trong

0.96

In

0.95

 trong

0.94

in

0.93

InThe

0.93

Dalam

0.92

Activations Density 0.025%

negations and expressions related to absence or unavailability

No Comments

No Known Activations