INDEX

Explanations

references to specific entities, actions, or parameters in technical contexts

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

future predictions for nations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

InjectAttribute

-0.61

tonsoft

-0.59

 للمعارف

-0.58

yntaxException

-0.54

ValueStyle

-0.53

 AspNetCore

-0.53

 صوتيه

-0.53

tanleria

-0.53

BeginContext

-0.52

VYMaps

-0.51

POSITIVE LOGITS

GEBURTS

0.52

 engineering

0.42

COL

0.41

 MOBILE

0.40

 Bache

0.40

🇧

0.39

 engineered

0.39

 Personal

0.38

 Kong

0.38

 personal

0.38

Activations Density 0.230%

references to specific entities, actions, or parameters in technical contexts

future predictions for nations

No Comments

No Known Activations