INDEX

Explanations

proper nouns, particularly names of people or places

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

astéroïdes

-1.05

:✨

-1.01

enumi

-0.92

 виправивши

-0.92

󠁴

-0.92

 مشين

-0.86

IsContent

-0.86

 nakalista

-0.86

 كومونز

-0.85

WebVitals

-0.83

POSITIVE LOGITS

0.68

–

0.65

0.64

«

0.63

’

0.63

0.61

®

0.61

0.57

Activations Density 0.753%

proper nouns, particularly names of people or places

No Comments

No Known Activations