INDEX

Explanations

scientific terms related to research findings and healthcare outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

+#+#

-0.88

Portail

-0.75

tvguidetime

-0.71

Hentet

-0.68

uxxxx

-0.63

########.

-0.59

Portale

-0.59

ImageContext

-0.58

extAlignment

-0.58

WriteTagHelper

-0.57

POSITIVE LOGITS

 should

0.61

can

0.60

 must

0.59

 fleste

0.51

 tarko

0.51

 entanto

0.50

 will

0.50

may

0.50

 ranges

0.49

 includes

0.48

Activations Density 0.624%

scientific terms related to research findings and healthcare outcomes

No Comments

No Known Activations