INDEX

Explanations

references to specific scientific terms, concepts, or entities related to health and medical research

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

+#+#

-0.89

providedIn

-0.79

'{@

-0.78

 nakalista

-0.77

 resourceCulture

-0.72

SOUNDBITE

-0.67

 dAtA

-0.66

 NSCoder

-0.65

 chi̍t

-0.65

NameInMap

-0.64

POSITIVE LOGITS

 regarding

0.59

 hinsichtlich

0.53

 especially

0.52

 overall

0.50

 throughout

0.47

ритори

0.47

canestro

0.46

 reflected

0.46

 égard

0.46

 spesielt

0.45

Activations Density 0.621%

references to specific scientific terms, concepts, or entities related to health and medical research

No Comments

No Known Activations