INDEX

Explanations

references to programming functions and their corresponding variables

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

onViewCreated

-0.57

InitVars

-0.54

antMatchers

-0.54

ngdoc

-0.53

 kaarangay

-0.53

 Himo

-0.53

lessed

-0.52

Bless

-0.52

RTEE

-0.52

 betweenstory

-0.50

POSITIVE LOGITS

or

0.78

或

0.63

หรือ

0.60

 или

0.59

 hoặc

0.58

0.55

 atau

0.53

 maupun

0.50

 یا

0.48

 või

0.47

Activations Density 1.397%

references to programming functions and their corresponding variables

No Comments

No Known Activations