INDEX

Explanations

negative constructions in sentences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 متعلقه

-0.83

GNP

-0.74

تقاوى

-0.73

Datuak

-0.72

CLS

-0.70

 itemList

-0.70

Ork

-0.69

Mep

-0.68

 Indra

-0.68

ลิต

-0.68

POSITIVE LOGITS

 been

1.07

 haven

1.03

 Haven

1.00

 hasn

0.91

 havent

0.89

 Been

0.82

 lately

0.78

 recent

0.77

 have

0.77

 BEEN

0.76

Activations Density 0.036%

negative constructions in sentences

No Comments

No Known Activations