INDEX

Explanations

instances of formatting markers, specifically the start of a new document or section

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/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.20.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

 Diſ

-0.69

 Reſ

-0.69

 Majefty

-0.67

 itſelf

-0.64

 reaſon

-0.63

 Conſ

-0.63

 ſeveral

-0.61

 purpoſe

-0.59

 Chriſt

-0.57

 thoſe

-0.56

POSITIVE LOGITS



0.70

SBATCH

0.69

StandardCharsets

0.67

 EconPapers

0.65

uxxxx

0.64

GEBURTSDATUM

0.63

만

0.60

⎩

0.60

APORE

0.59

 LIABLE

0.58

Activations Density 0.033%

instances of formatting markers, specifically the start of a new document or section

No Comments

No Known Activations