INDEX

Explanations

variations of the letter 'c' in words or tokens

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 ponts

-0.61

 متحده

-0.56

rungsseite

-0.53

GIH

-0.49

CGContext

-0.47

 sond

-0.46

al

-0.46

 nive

-0.46

 sembra

-0.46

 lont

-0.46

POSITIVE LOGITS

2.02

 autorytatywna

0.84

awtextra

0.84

adaptiveStyles

0.78

 levit

0.77

Viited

0.75

#+#

0.74

Sucesor

0.72

 ویکی‌پدیا

0.71

onucle

0.67

Activations Density 0.178%

variations of the letter 'c' in words or tokens

No Comments

No Known Activations