INDEX

Explanations

phrases indicating negation or exclusion

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

IsMutable

-0.71

 toll

-0.70

ArgsConstructor

-0.68

 resourceCulture

-0.64

principalColumn

-0.61

exitRule

-0.61

expandindo

-0.61

 gynhyrchwyd

-0.60

ViewImports

-0.57

ajoz

-0.56

POSITIVE LOGITS

 mention

1.36

 Mention

1.04

mention

1.03

 plus

1.00

 mentioning

0.99

 mentions

0.94

plus

0.93

Plus

0.93

 Plus

0.91

 mencionar

0.90

Activations Density 0.077%

phrases indicating negation or exclusion

No Comments

No Known Activations