INDEX

Explanations

mathematical expressions involving positive and negative operations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 snippetHide

-0.65

)))));

-0.61

styleType

-0.55

 maschile

-0.53

 privatisation

-0.51

readyState

-0.49

 engraçadas

-0.49

 Landschafts

-0.49

 gripped

-0.49

grid

-0.49

POSITIVE LOGITS

AnimationsModule

0.66

rogly

0.63

MemoryWarning

0.63

новништво

0.62

исленность

0.61

onActivityResult

0.61

vfill

0.54

المناصب

0.53

 pièce

0.52

protoc

0.52

Activations Density 0.698%

mathematical expressions involving positive and negative operations

No Comments

No Known Activations