INDEX

Explanations

terminology related to long-term and short-term concepts or effects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

migrationBuilder

-0.75

 Baillargeon

-0.65

interopRequire

-0.64

UrlResolution

-0.61

AndEndTag

-0.61

存于互联网档案馆

-0.60

 okuyayım

-0.60

IGraphics

-0.57

DotNetBar

-0.57

WebVitals

-0.56

POSITIVE LOGITS

 term

1.98

term

1.76

 Term

1.52

Term

1.50

 TERM

1.44

TERM

1.35

 terms

1.18

 termen

1.17

terms

1.16

 terme

1.15

Activations Density 0.169%

terminology related to long-term and short-term concepts or effects

No Comments

No Known Activations