INDEX

Explanations

phrases that indicate returning or going back to a previous state or location

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

pushFollow

-0.70

 disambiguazione

-0.59

__*/

-0.59

служи

-0.57

Geplaatst

-0.57

VideoCapture

-0.55

db

-0.55

 ENTITY

-0.55

 mendatang

-0.55

ApiModelProperty

-0.55

POSITIVE LOGITS

回到

0.78

 reverting

0.65

回到了

0.65

 tilbake

0.63

 regain

0.62

 resuming

0.61

 tornare

0.61

+#+#

0.59

setVerticalGroup

0.59

 retrouve

0.59

Activations Density 0.116%

phrases that indicate returning or going back to a previous state or location

No Comments

No Known Activations