INDEX

Explanations

references to moments or events, particularly in dialogue

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

Efq

-0.96

 Houſe

-0.93

+:+

-0.93

 itſelf

-0.93

 Anſ

-0.92

 myſelf

-0.91

 Monfieur

-0.91

+#+#

-0.91

 houſe

-0.89

aarrggbb

-0.86

POSITIVE LOGITS

‘

0.50

0.46

has

0.42

“

0.41

 full

0.41

full

0.40

↵

0.39

 continue

0.38

Activations Density 0.128%

references to moments or events, particularly in dialogue

No Comments

No Known Activations