INDEX

Explanations

references to individual elements in lists or examples

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

li

-0.47

Invoke

-0.41

“

-0.41

 hiç

-0.40

už

-0.40

opers

-0.39

‘

-0.39

מים

-0.39

POSITIVE LOGITS

 Majefty

1.15

 itſelf

1.09

 individually

1.05

Efq

1.04

 Monfieur

1.03

 myſelf

1.01

 poffible

0.98

 themſelves

0.97

 Jefus

0.95

 himſelf

0.94

Activations Density 0.323%

references to individual elements in lists or examples

No Comments

No Known Activations