INDEX

Explanations

comparative phrases and adjectives related to effectiveness and improvement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

 تضيفلها

-0.82

人不

-0.73

DllImport

-0.72

 estimés

-0.70

={`${

-0.62

expandindo

-0.59

ازم

-0.59

Quoting

-0.58

któ

-0.58

Personendaten

-0.57

POSITIVE LOGITS

ctory

0.56

 predecess

0.55

 favourable

0.55

क्षित

0.52

 favorable

0.52

şen

0.51

 possibile

0.51

ตร์

0.50

 <=",

0.49

ftagPool

0.49

Activations Density 0.373%

comparative phrases and adjectives related to effectiveness and improvement

No Comments

No Known Activations