INDEX

Explanations

new beginnings or introductions in text

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

Abitanti

-0.73

 ligiloj

-0.73

 didst

-0.72

 viewDid

-0.71

ográficos

-0.71

Obrázky

-0.69

 Wikisource

-0.69

rungsseite

-0.66

 Rollo

-0.64

 चीज़ों

-0.64

POSITIVE LOGITS

the

0.59

Acquire

0.52

()",

0.52

Analyze

0.51

0.49

AndSet

0.49

 Probe

0.48

 Acquire

0.47

álen

0.47

互联网档案馆

0.47

Activations Density 0.167%

new beginnings or introductions in text

No Comments

No Known Activations