INDEX

Explanations

the beginning of a text or document

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

after capitalized words

np_acts-logits-general · gemini-2.0-flash

starting phrases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/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.20.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

 propOrder

-0.73

featureID

-0.72

OGND

-0.71

 betweenstory

-0.68

invokeLater

-0.62

prüche

-0.57

complexType

-0.56

rungsseite

-0.56

 Reim

-0.55

+#+#

-0.55

POSITIVE LOGITS

TagHelper

0.66

await

0.64

 await

0.57

BASEPATH

0.48

 referrerpolicy

0.46

TagHelpers

0.46

 baik

0.46

ValueStyle

0.45

valget

0.44

enumii

0.44

Activations Density 0.012%

the beginning of a text or document

after capitalized words

starting phrases

No Comments

No Known Activations