INDEX

Explanations

numerical statistics and accompanying annotations

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

 fourth

-0.83

⁴

-0.74

 four

-0.70

 keempat

-0.69

 FOURTH

-0.67

-0.66

 Forty

-0.66

 Fourth

-0.64

 quattro

-0.64

 FOUR

-0.64

POSITIVE LOGITS

 FetchType

0.57

 Seven

0.53

0.48

0.47

0.46

 VIII

0.43

VII

0.42

八

0.42

 jsPsych

0.41

Activations Density 0.421%

numerical statistics and accompanying annotations

No Comments

No Known Activations