INDEX

Explanations

occurrences of the word "notice" in various forms and 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 руками

-0.70

Bag

-0.67

ylvan

-0.61

ništvo

-0.61

 Bran

-0.61

dengan

-0.61

stdlib

-0.59

 McFarland

-0.59

 '../../../

-0.59

TOTAL

-0.58

POSITIVE LOGITS

 notice

2.34

 Notice

2.24

notice

2.13

Notice

2.12

 NOTICE

2.11

 notices

2.09

NOTICE

1.99

 Notices

1.96

Notices

1.84

notices

1.68

Activations Density 0.059%

occurrences of the word "notice" in various forms and contexts

No Comments

No Known Activations