INDEX

Explanations

comparative phrases indicating thresholds or limits

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

RenderAtEndOf

-0.46

hul

-0.44

mer

-0.43

zookeeper

-0.42

 FormsModule

-0.41

erville

-0.40

 बस

-0.40

 counts

-0.39

CBS

-0.39

jointe

-0.39

POSITIVE LOGITS

AndEndTag

0.85

GEBURTSDATUM

0.82

 than

0.82

 propOrder

0.80

 >=",

0.76

ंदीखरीदारी

0.76

enumi

0.74

URLException

0.73

 THAN

0.72

 beyond

0.70

Activations Density 0.670%

comparative phrases indicating thresholds or limits

No Comments

No Known Activations