INDEX

Explanations

expressions of apology or regret

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

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

RegistryLite

-0.87

});*/

-0.82

GHIJKLM

-0.79

styleType

-0.79

AccessorTable

-0.78

AntiForgeryToken

-0.76

 дописавши

-0.76

+#+#

-0.76

 ThemeData

-0.76

Xna

-0.74

POSITIVE LOGITS

 about

0.67

 excuse

0.54

about

0.53

Sorry

0.52

excuse

0.50

we

0.50

for

0.50

Зміст

0.49

yy

0.48

jande

0.47

Activations Density 0.036%

expressions of apology or regret

No Comments

No Known Activations