INDEX

Explanations

references to current systems or frameworks that are in place

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

 énergé

-0.69

 télévis

-0.65

MLLoader

-0.64

ècie

-0.64

 chimique

-0.62

 complètes

-0.61

ăsp

-0.60

 particulières

-0.60

 affinch

-0.59

CrossRef

-0.59

POSITIVE LOGITS

 existing

2.21

Existing

2.02

 Existing

2.02

existing

1.99

 EXISTING

1.75

 bestaande

1.52

既存

1.47

 existente

1.39

 preexisting

1.37

 bestehende

1.32

Activations Density 0.123%

references to current systems or frameworks that are in place

No Comments

No Known Activations