INDEX

Explanations

instances of the letter 'e' in varying contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

Personensuche

-0.80

ViewImports

-0.75

JMenu

-0.71

AsUp

-0.70

 Daarna

-0.70

 виправивши

-0.69

AccessorTable

-0.68

omiast

-0.68

гава

-0.67

 Мексичка

-0.67

POSITIVE LOGITS

譬

0.76

 particularly

0.70

例

0.67

 अर्

0.67

 especially

0.65

 including

0.63

 such

0.61

 ESPEC

0.58

Pře

0.58

Activations Density 0.298%

instances of the letter 'e' in varying contexts

No Comments

No Known Activations