INDEX

Explanations

print statements in code

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

LookAnd

-0.68

__::

-0.62

 يتيمه

-0.61

 صوتيه

-0.56

MigrationBuilder

-0.55

 ddelweddau

-0.54

 Administrativna

-0.53

 незавершена

-0.51

uxxxx

-0.51

 betweenstory

-0.49

POSITIVE LOGITS

WriteLine

0.81

Println

0.74

println

0.69

iostream

0.59

 println

0.56

writerow

0.56

GOTREF

0.52

 defaultstate

0.49

printf

0.49

console

0.48

Activations Density 0.052%

print statements in code

No Comments

No Known Activations