INDEX

Explanations

references to time and temporal concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 vuestros

-0.57

 vuestro

-0.54

 cejas

-0.47

 vuestra

-0.46

 rojas

-0.45

立てる

-0.44

 capucha

-0.43

 Públicas

-0.42

CLUDING

-0.42

 réception

-0.42

POSITIVE LOGITS

Time

1.20

 Time

1.20

time

1.20

 time

1.20

TIME

1.16

 TIME

1.12

 getTime

1.06

 setTime

1.03

getTime

1.00

 tyme

0.98

Activations Density 0.161%

references to time and temporal concepts

No Comments

No Known Activations