INDEX

Explanations

references to sections, clauses, or articles related to legal or regulatory documents

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

">//

-0.59

osu

-0.52

-0.50

г

-0.49

נע

-0.46

 رک

-0.46

坐

-0.45

 katanya

-0.44

geschlossen

-0.44

TagHelper

-0.43

POSITIVE LOGITS

abestanden

0.80

 beginnetje

0.73

tonode

0.65

 betweenstory

0.60

Демографія

0.60

featureID

0.59

 Monfieur

0.59

 jScrollPane

0.58

 itſelf

0.56

expandindo

0.55

Activations Density 1.350%

references to sections, clauses, or articles related to legal or regulatory documents

No Comments

No Known Activations