INDEX

Explanations

instances of the word "round" 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 @ 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

脚注の使い方

-0.86

 للمعارف

-0.86

 Roskov

-0.85

]--;

-0.83

 ModelExpression

-0.80

{}{}

-0.77

المكان

-0.76

Referències

-0.72

 &___

-0.72

 useAuth

-0.71

POSITIVE LOGITS

 round

4.18

round

3.86

Round

3.73

 Round

3.69

 ROUND

3.61

ROUND

3.34

 rounds

3.34

 Rounds

2.86

rounds

2.78

Rounds

2.45

Activations Density 0.060%

instances of the word "round" in various contexts

No Comments

No Known Activations