INDEX

Explanations

terms associated with product development and evaluation processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

-0.67

the

-0.60

-0.59

-0.57

The

-0.56

an

-0.56

to

-0.55

POSITIVE LOGITS

expandindo

1.20

 propOrder

1.09

Vidite

1.00

 itſelf

0.96

 ་་

0.94

 myſelf

0.94

 doubtnut

0.92

featureID

0.91

 raiſ

0.89

 chofe

0.87

Activations Density 0.601%

terms associated with product development and evaluation processes

No Comments

No Known Activations