INDEX

Explanations

quantitative data related to measurements and averages

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

 дописавши

-0.70

 myſelf

-0.66

 Jefus

-0.66

 itſelf

-0.65

 Chriſt

-0.60

Eſ

-0.60

 Houſe

-0.60

cuál

-0.59

 météo

-0.59

 pleaſure

-0.59

POSITIVE LOGITS

 total

0.87

SourceChecksum

0.77

total

0.73

LookAnd

0.63

 average

0.61

 Total

0.60

+:+

0.60

setVerticalGroup

0.59

 totale

0.58

 totalt

0.57

Activations Density 0.653%

quantitative data related to measurements and averages

No Comments

No Known Activations