INDEX

Explanations

instances of the word "represent" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ueger

-0.63

低的

-0.58

Mui

-0.57

воро

-0.57

Closeable

-0.57

Autowired

-0.56

 дро

-0.53

cal

-0.53

 suspicion

-0.53

 OkHttpClient

-0.52

POSITIVE LOGITS

 represent

3.27

 representing

3.13

 Represent

3.04

 represents

3.04

Represent

2.99

represent

2.94

 REPRESENT

2.88

 Representing

2.87

 representation

2.86

represents

2.81

Activations Density 0.101%

instances of the word "represent" and its variations

No Comments

No Known Activations