INDEX

Explanations

the word "latest" in various contexts

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

latest news and updates

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

XmlAccessorType

-0.50

charCode

-0.45

complexContent

-0.44

 charging

-0.44

cæ

-0.43

awtextra

-0.43

 iscri

-0.43

IMC

-0.43

 autorytatywna

-0.42

ckså

-0.42

POSITIVE LOGITS

 latest

1.77

latest

1.75

Latest

1.63

 Latest

1.52

 LATEST

1.49

LATEST

1.32

最新

1.30

最新的

1.21

 最新

1.21

 neuesten

1.08

Activations Density 0.004%

the word "latest" in various contexts

latest news and updates

No Comments

No Known Activations