INDEX

Explanations

expressions of personal opinion and emotional response towards literature

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

Commas and periods followed by discourse markers

np_acts-logits-general · gemini-2.0-flash

acknowledgment and admission

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 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

 متعلقه

-0.94

 виправивши

-0.76

 estekak

-0.74

tdessen

-0.73

Portale

-0.72

 AssemblyProduct

-0.69

 Biôgrafia

-0.69

Diweddarwch

-0.67

 ModelAndView

-0.67

 dAtA

-0.67

POSITIVE LOGITS

yes

1.10

 Granted

0.94

 admittedly

0.92

Granted

0.91

Yes

0.90

Yes

0.82

 certes

0.78

 truth

0.75

 frankly

0.74

 granted

0.74

Activations Density 0.273%

expressions of personal opinion and emotional response towards literature

Commas and periods followed by discourse markers

acknowledgment and admission

No Comments

No Known Activations