INDEX

Explanations

phrases indicating strong affirmation or certainty

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

abaret

-0.63

nap

-0.63

 tradition

-0.61

OTION

-0.60

ாய

-0.58

Tradition

-0.58

 Irving

-0.58

 Tradition

-0.58

erl

-0.58

Pico

-0.57

POSITIVE LOGITS

 definitely

1.88

 Definitely

1.74

Definitely

1.67

definitely

1.65

 definately

1.60

 definite

1.43

 certainly

1.38

definite

1.28

 Certainly

1.28

certainly

1.17

Activations Density 0.070%

phrases indicating strong affirmation or certainty

No Comments

No Known Activations