INDEX

Explanations

terms related to statistical results and agreements in research

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 للمعارف

-0.57

 виправивши

-0.55

ensuremath

-0.50

 يتيمه

-0.44

 ElementRef

-0.44

BASEPATH

-0.43

expandindo

-0.43

moveToFirst

-0.43

 NotImplemented

-0.40

smo

-0.40

POSITIVE LOGITS

 betweenstory

0.81

ंदीखरीदारी

0.74

adpleegd

0.72

 estimés

0.66

richTextPanel

0.64

ArrowToggle

0.64

олові

0.62

المناصب

0.61

 commerciales

0.61

theros

0.60

Activations Density 1.566%

terms related to statistical results and agreements in research

No Comments

No Known Activations