INDEX

Explanations

indicators of ongoing or repeating situations or actions in narratives

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

NUMX

-1.27

 Савезне

-1.03

 تضيفلها

-0.95

—

-0.89

Erreferentziak

-0.89

iffance

-0.89

bkz

-0.87

felves

-0.85

\{\\

-0.85

Бележки

-0.85

POSITIVE LOGITS

ru

0.63

↵↵

0.58

…

0.58

<eos>

0.57

…

0.53

“

0.53

la

0.51

plus

0.51

pre

0.51

ho

0.50

Activations Density 0.138%

indicators of ongoing or repeating situations or actions in narratives

No Comments

No Known Activations