INDEX

Explanations

mentions of inventions or devices, particularly their uses and historical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

NameInMap

-0.62

 Italijanski

-0.58

AndEndTag

-0.57

AnimationsModule

-0.57

ficulties

-0.55

StoryboardSegue

-0.54

RUnlock

-0.54

⪜

-0.51

MockMvc

-0.50

 يتيمه

-0.50

POSITIVE LOGITS

 invention

0.47

 invented

0.46

 technology

0.45

 used

0.40

 ubiquitous

0.39

 prolon

0.39

 usage

0.39

 equipment

0.38

 tool

0.38

 glasses

0.37

Activations Density 0.090%

mentions of inventions or devices, particularly their uses and historical context

No Comments

No Known Activations