INDEX

Explanations

structured academic language and citations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

randrange

-0.58

Autom

-0.51

נה

-0.44

ništ

-0.42

LD

-0.42

プリング

-0.41

旺

-0.41

 aiuto

-0.41

HCR

-0.40

 Profitez

-0.40

POSITIVE LOGITS

addGap

0.74

WriteTagHelper

0.69

发表于

0.69

Authors

0.66

 Lordships

0.66

 Affiliations

0.65

 propOrder

0.65

Autoritní

0.63

ollectionView

0.63

awtextra

0.63

Activations Density 1.623%

structured academic language and citations

No Comments

No Known Activations