INDEX

Explanations

values related to numeric identification or data handling

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

Code snippets or programming-related text

np_acts-logits-general · gemini-2.0-flash

numbers, code, or math separators

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

ArgsConstructor

-0.70

StoreMessageInfo

-0.68

 nonUne

-0.67

 esternos

-0.64

بوابة

-0.64

abetes

-0.63

enumi

-0.61

SOUNDBITE

-0.60

sizeCache

-0.59

 ouvertes

-0.58

POSITIVE LOGITS

0.94

0.61

 ninth

0.60

0.59

0.55

 viewType

0.53

0.51

 XCTest

0.48

0.46

Activations Density 0.051%

values related to numeric identification or data handling

Code snippets or programming-related text

numbers, code, or math separators

No Comments

No Known Activations