INDEX

Explanations

formatted output strings or placeholders used in programming, particularly with the printf function

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

SequentialGroup

-0.75

adaptiveStyles

-0.73

原始内容存档于

-0.66

 Sarko

-0.63

WebVitals

-0.63

 joaat

-0.63

 pronouns

-0.63

,\,

-0.62

migrationBuilder

-0.62

lidene

-0.61

POSITIVE LOGITS

("%

1.83

"%

1.58

("%

1.52

"%

1.18

('%

1.16

,"%

1.13

'%

1.12

="%

1.06

'%

1.05

("%.

0.95

Activations Density 0.042%

formatted output strings or placeholders used in programming, particularly with the printf function

No Comments

No Known Activations