INDEX

Explanations

specific numerical values or data points that illustrate important results or findings

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

Code snippets or unusual characters

np_acts-logits-general · gemini-2.0-flash

appears after "There" or "amplitudes"

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

RIE

-0.61

tri

-0.61

InteropServices

-0.57

Affirmed

-0.54

ISTIC

-0.54

 عاش

-0.54

-0.53

mene

-0.52

uso

-0.51

 getRequest

-0.51

POSITIVE LOGITS

WithIOException

0.96

Portail

0.85

ChildScrollView

0.75

 ujednoznacz

0.72

 Paglinawan

0.72

 المعيارى

0.69

rungsseite

0.69

 विश्वसनीयता

0.66

 وتسجيلات

0.66

enumii

0.65

Activations Density 0.068%

specific numerical values or data points that illustrate important results or findings

Code snippets or unusual characters

appears after "There" or "amplitudes"

No Comments

No Known Activations