INDEX

Explanations

references to various groups or classifications in data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.27.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

électricité

-0.52

AndEndTag

-0.50

 iNdEx

-0.50

"]));

-0.48

 ioutil

-0.47

 electricidad

-0.46

 NavController

-0.45

harapkan

-0.43

 îna

-0.43

SEVERE

-0.43

POSITIVE LOGITS

 group

1.06

 Group

1.05

Group

0.98

 GROUP

0.98

 getGroup

0.96

group

0.94

 groups

0.86

GROUP

0.86

roup

0.85

getGroup

0.81

Activations Density 0.184%

references to various groups or classifications in data

No Comments

No Known Activations