INDEX

Explanations

comparative adjectives and phrases indicating differences in quality or quantity

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

chappement

-0.70

ckley

-0.63

ψε

-0.63

 препратки

-0.60

 linkovi

-0.59

 virtuel

-0.57

Lorem

-0.56

 tomb

-0.56

NUE

-0.55

artem

-0.55

POSITIVE LOGITS

 older

0.91

 younger

0.88

 newer

0.81

 rarer

0.78

 milder

0.75

 Older

0.74

 Newer

0.74

Older

0.74

 älteren

0.73

 дописавши

0.72

Activations Density 0.201%

comparative adjectives and phrases indicating differences in quality or quantity

No Comments

No Known Activations

comparative adjectives and phrases indicating differences in quality or quantity

No Comments

No Known Activations