INDEX

Explanations

phrases that indicate research findings or results

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

 المعيارى

-0.73

tagHelperRunner

-0.60

 ethics

-0.59

MemoryWarning

-0.58

AutoScale

-0.57

anama

-0.54

buka

-0.54

 handle

-0.54

 onAnimation

-0.53

 Harts

-0.53

POSITIVE LOGITS

ragamo

0.58

Viitteet

0.56

PMID

0.56

Findings

0.48

 barbell

0.48

 EVIDENCE

0.47

 ejus

0.47

Халык

0.46

Šaltiniai

0.46

 cuadrada

0.46

Activations Density 0.551%

phrases that indicate research findings or results

No Comments

No Known Activations