INDEX

Explanations

the concept of "newness" or "updates."

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

new followed by a noun

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.24.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

 PeEnEo

-0.48

heme

-0.40

anth

-0.40

OGND

-0.40

sector

-0.39

 setType

-0.38

să

-0.38

 Comunicação

-0.38

UrlResolution

-0.38

 Whitehead

-0.38

POSITIVE LOGITS

AlterField

0.52

 versions

0.45

 version

0.45

脚注の使い方

0.43

makeConstraints

0.43

tvguidetime

0.43

 ContentValues

0.43

jsxFileName

0.42

SBATCH

0.41

InputTagHelper

0.41

Activations Density 0.074%

the concept of "newness" or "updates."

new followed by a noun

No Comments

No Known Activations