INDEX

Explanations

comments and preprocessor directives in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

SuspendLayout

-0.61

로그램

-0.56

 useRef

-0.55

nestjs

-0.53

rtype

-0.52

 IBOutlet

-0.52

TokenNameLPAREN

-0.52

 kteří

-0.50

Халык

-0.50

tagHelper

-0.50

POSITIVE LOGITS



0.95

UnsafeEnabled

0.80

 متعلقه

0.79

 שוליים

0.72

تقاوى

0.70

uxxxx

0.69

<<<<<<<

0.65

henswürdigkeiten

0.63

 виправивши

0.63

 Roskov

0.63

Activations Density 0.092%

comments and preprocessor directives in code

No Comments

No Known Activations