INDEX

Explanations

phrases related to time, particularly those indicating recent or past events

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

 فريبيس

-1.19

 Roskov

-0.98

Personensuche

-0.93

Cyfeiriadau

-0.92

 eorum

-0.82

Hentet

-0.80

 transfieras

-0.80

 незавершена

-0.78

 ostavi

-0.74

 varandra

-0.74

POSITIVE LOGITS

few

1.10

decade

0.99

 couple

0.93

few

0.69

 month

0.62

Few

0.59

couple

0.59

 months

0.57

 century

0.57

ten

0.56

Activations Density 0.069%

phrases related to time, particularly those indicating recent or past events

No Comments

No Known Activations