INDEX

Explanations

occurrences of the letter 'a' 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 @ 1-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_1/width_16k/average_l0_105

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.hook_mlp_out

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

-2.44

an

-2.00

 sebuah

-1.11

 eine

-1.04

 einen

-1.03

 seorang

-1.01

 einem

-1.01

 isang

-1.00

einem

-1.00

 Sebuah

-0.99

POSITIVE LOGITS

 AttributeSet

0.64

ComponentScan

0.58

AutoScaleMode

0.55

+#+#

0.55

InputBorder

0.55

 Roskov

0.54

 Italijanski

0.54

曖昧さ回避

0.54

 Acton

0.53

 ArrayAdapter

0.52

Activations Density 0.425%

occurrences of the letter 'a' in various contexts

No Comments

No Known Activations