INDEX

Explanations

mathematical expressions and notations involving variables and their powers

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

Cr

-0.58

chanical

-0.55

cr

-0.51

iotensin

-0.51

 Henry

-0.49

DebuggerNonUser

-0.49

тя

-0.49

arj

-0.49

пя

-0.48

ǒ

-0.48

POSITIVE LOGITS

 متعلقه

0.86

 betweenstory

0.84

StoryboardSegue

0.80

 externi

0.75

saraba

0.73

ValueStyle

0.73

thée

0.73

 незавершена

0.72

المناصب

0.71

makeConstraints

0.70

Activations Density 0.899%

mathematical expressions and notations involving variables and their powers

No Comments

No Known Activations