INDEX

Explanations

instances of the word "notice" in various forms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

-0.92

-0.91

num

-0.83

my

-0.78

-0.77

 McFarland

-0.71

op

-0.71

:\/\/

-0.69

ul

-0.68

-0.67

POSITIVE LOGITS

 Notice

1.14

 NOTICE

1.10

NOTICE

1.09

 Notices

1.03

LikeLike

1.02

 notice

0.99

 notices

0.97

Notice

0.97

 noticed

0.96

notice

0.96

Activations Density 0.137%

instances of the word "notice" in various forms

No Comments

No Known Activations