INDEX

Explanations

instances of the word "enter."

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

OwnProperty

-0.67

*/].

-0.66

maketitle

-0.62

éndole

-0.61

yii

-0.61

NumOf

-0.60

zahlt

-0.59

 Meksiku

-0.58

大家

-0.57

schmidt

-0.57

POSITIVE LOGITS

 entered

2.62

 enter

2.61

 enters

2.53

 entering

2.47

 Entering

2.39

Entering

2.23

entered

2.22

 Entered

2.10

enters

2.08

 Enter

2.05

Activations Density 0.099%

instances of the word "enter."

No Comments

No Known Activations