INDEX

Explanations

instances of similarity and comparison between elements or subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

autique

-0.54

ดุ

-0.52

 otherwise

-0.51

 Einzelnen

-0.49

ToEnd

-0.49

ContentAsync

-0.48

jasper

-0.47

ời

-0.47

otherwise

-0.46

 saites

-0.46

POSITIVE LOGITS

 similarly

0.87

 ebenfalls

0.84

 similar

0.83

similar

0.75

 betweenstory

0.73

同じく

0.72

 SIMILAR

0.69

InputTagHelper

0.68

Similar

0.68

同樣

0.67

Activations Density 0.551%

instances of similarity and comparison between elements or subjects

No Comments

No Known Activations