INDEX

Explanations

occurrences of the letters 'a' and 'b' in various contexts, possibly indicating a focus on specific grammatical elements or categories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

zió

-0.57

iyaki

-0.53

ogna

-0.52

innocent

-0.52

 FileInputStream

-0.50

tlement

-0.50

GoogleApiClient

-0.50

telle

-0.48

 Larson

-0.48

bori

-0.47

POSITIVE LOGITS

UnsafeEnabled

1.10

/******/

1.03

'{@

1.02

 ویکی‌پدیا

0.98

 EconPapers

0.97

 disambiguazione

0.88

Datuak

0.88

تقاوى

0.88

StoreMessageInfo

0.85

存于互联网档案馆

0.83

Activations Density 0.038%

occurrences of the letters 'a' and 'b' in various contexts, possibly indicating a focus on specific grammatical elements or categories

No Comments

No Known Activations