INDEX

Explanations

occurrences of specific terms related to publication and timelines

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

webElement

-0.74

üedad

-0.55

 upcoming

-0.51

newInstance

-0.51

casus

-0.50

 Baru

-0.50

 caufe

-0.49

new

-0.49

abha

-0.49

南浔

-0.49

POSITIVE LOGITS

enumi

0.81

BeginInit

0.65

enumii

0.62

GIVEREF

0.59

<bos>

0.57

tagext

0.51

 previous

0.50

previous

0.50

 précédentes

0.50

GEBURTSDATUM

0.49

Activations Density 0.535%

occurrences of specific terms related to publication and timelines

No Comments

No Known Activations