INDEX

Explanations

words and phrases related to academic publications or scientific research

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

تقاوى

-0.57

 BoxDecoration

-0.53

RenderAtEndOf

-0.52

 OFDb

-0.52

adpleegd

-0.49

StructEnd

-0.48

 ***!

-0.47

 klar

-0.47

RefNanny

-0.47

WebVitals

-0.46

POSITIVE LOGITS

AndEndTag

0.76

URLException

0.68

 aDecoder

0.66

outSlope

0.60

 décontract

0.58

oas

0.57

 dolayı

0.56

msgSender

0.56

 podjela

0.56

 Semp

0.55

Activations Density 0.113%

words and phrases related to academic publications or scientific research

No Comments

No Known Activations