INDEX

Explanations

the occurrence of the word "three" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 Athenians

-0.81

Efq

-0.77

 chapels

-0.74

 Lipschitz

-0.73

MAV

-0.72

 Plutarch

-0.72

 Cæsar

-0.71

 Mongols

-0.71

 Poincar

-0.70

 ballads

-0.70

POSITIVE LOGITS

 three

2.58

two

2.38

 four

2.23

three

2.10

two

1.86

 trois

1.82

 five

1.82

six

1.69

 drei

1.66

four

1.65

Activations Density 0.215%

the occurrence of the word "three" in various contexts

No Comments

No Known Activations