INDEX

Explanations

instances of the word "one" or its variants in different contexts

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

 fumée

-0.85

 suivantes

-0.79

Personendaten

-0.77

 économie

-0.74

 pérd

-0.72

 myſelf

-0.70

ásban

-0.69

 Sociales

-0.69

 armée

-0.69

 houſe

-0.69

POSITIVE LOGITS

1.18

 एक

1.03

एक

1.00

een

0.98

 một

0.98

 یک

0.95

Een

0.94

 einem

0.94

 Eine

0.93

Eine

0.93

Activations Density 0.021%

instances of the word "one" or its variants in different contexts

No Comments

No Known Activations