INDEX

Explanations

expressions of appreciation or gratitude

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

ing

-0.86

-0.76

ings

-0.74

ING

-0.73

ness

-0.71

est

-0.71

RLock

-0.68

-0.67

iness

-0.67

miary

-0.65

POSITIVE LOGITS

 myſelf

1.19

 Forumite

1.07

 themſelves

1.07

 itſelf

1.03

 ſeveral

0.97

uate

0.95

^(@)

0.93

 poffible

0.92

unate

0.90

 himſelf

0.90

Activations Density 0.342%

expressions of appreciation or gratitude

No Comments

No Known Activations