INDEX

Explanations

elements of code or structured data formats with specific attributes like headers or content types

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

󠁿

-0.93

μβρίου

-0.82

 سكانية

-0.77

fortawesome

-0.66

__*/

-0.63

CJK

-0.63

">(</

-0.61

WithFormat

-0.60

üyada

-0.58

interopRequire

-0.58

POSITIVE LOGITS

 Majefty

0.83

 fhew

0.78

 reaſon

0.76

 Chriftian

0.76

 HttpNotFound

0.75

 poffe

0.75

 ſche

0.73

 Reſ

0.72

 fubject

0.72

 raiſ

0.72

Activations Density 19.338%

elements of code or structured data formats with specific attributes like headers or content types

No Comments

No Known Activations