INDEX

Explanations

comparative adjectives and their contexts related to ease or difficulty

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

Following "easy," "hard," or "difficult."

np_acts-logits-general · gemini-2.0-flash

easy/difficult to

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

NameInMap

-1.01

AccessorTable

-0.91

SharedCtor

-0.81

 kasarigan

-0.81

CPtr

-0.74

UrlResolution

-0.70

__':

-0.69

IndentedString

-0.67

 eventdata

-0.66

yntaxException

-0.66

POSITIVE LOGITS

to

1.64

to

0.87

To

0.78

 να

0.76

ToRead

0.74

ToLoad

0.71

ToDisplay

0.67

To

0.67

ToAdd

0.62

DataTo

0.61

Activations Density 0.213%

comparative adjectives and their contexts related to ease or difficulty

Following "easy," "hard," or "difficult."

easy/difficult to

No Comments

No Known Activations