INDEX

Explanations

terms and concepts related to typography or font rendering

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 Bick

-0.78

 Barclay

-0.75

usermodel

-0.73

Aur

-0.72

く

-0.71

Становништво

-0.69

 Dwyer

-0.68

 Chwiliwch

-0.68

eqn

-0.68

POSITIVE LOGITS

2.19

ات

1.11

ség

1.07

ים

1.04

︎

1.02

venirs

0.96

).'

0.91

۰۰

0.89

ся

0.89

')")

0.88

Activations Density 3.502%

terms and concepts related to typography or font rendering

No Comments

No Known Activations