INDEX

Explanations

references to "slides" and related terms in scientific contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

reportWebVitals

-0.55

Disliked

-0.52

LookAnd

-0.51

RectangleBorder

-0.51

+#+#

-0.50

 Numerade

-0.50

NameInMap

-0.48

StructEnd

-0.47

setVerticalGroup

-0.47

Související

-0.47

POSITIVE LOGITS

 slide

0.85

 Slide

0.84

Slide

0.82

 slides

0.80

slide

0.74

slides

0.65

 Slides

0.62

SLIDE

0.53

Slides

0.51

スライド

0.51

Activations Density 0.137%

references to "slides" and related terms in scientific contexts

No Comments

No Known Activations