INDEX

Explanations

technical terms and jargon related to scientific research and methodologies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

lujah

-0.66

 &___

-0.65

TypedDataSet

-0.64

verständlich

-0.63

orianCalendar

-0.62

roek

-0.62

ailleurs

-0.60

 <>",

-0.60

 AssemblyCompany

-0.59

 ChromeDriver

-0.57

POSITIVE LOGITS

1.48

expandindo

0.72

‑

0.71

‐

0.70

-...

0.68

 sockaddr

0.67

тнес

0.63

eqn

0.63

 nordrhein

0.63

TagHelpers

0.62

Activations Density 2.013%

technical terms and jargon related to scientific research and methodologies

No Comments

No Known Activations