INDEX

Explanations

the word "United" when it refers to the United States

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 Orissa

-0.87

évaluateur

-0.87

 Roskov

-0.87

 Meksiku

-0.84

 NSCoder

-0.81

InjectAttribute

-0.77

 ModelExpression

-0.76

 BORROW

-0.75

NameInMap

-0.75

featureID

-0.73

POSITIVE LOGITS

 United

3.55

United

3.31

 UNITED

2.83

UNITED

2.58

united

2.32

 united

2.25

 Vereinigten

1.84

Utd

1.46

 Verenigde

1.45

 Vereinigte

1.41

Activations Density 0.071%

the word "United" when it refers to the United States

No Comments

No Known Activations