INDEX

Explanations

the word "each" in various 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

er

-0.64

SUT

-0.62

im

-0.62

Goy

-0.61

 pinos

-0.60

shit

-0.57

Bon

-0.57

 fores

-0.56

 Wiseman

-0.56

ter

-0.56

POSITIVE LOGITS

EACH

2.30

 each

2.23

 EACH

2.18

 Each

2.12

each

2.11

Each

2.08

Chaque

1.84

 Chaque

1.74

 chaque

1.66

 ciasc

1.59

Activations Density 0.101%

the word "each" in various contexts

No Comments

No Known Activations