INDEX

Explanations

descriptive phrases related to visual appearances and technical details

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 HasFactory

-0.84

WebVitals

-0.80

extAlignment

-0.79

 незавершена

-0.77

PreferredItem

-0.70

styleType

-0.68

SourceChecksum

-0.67

InputBorder

-0.67

migrationBuilder

-0.67

 Theſe

-0.66

POSITIVE LOGITS

 incorrectly

0.57

mis

0.57

 unnecessarily

0.56

 sometimes

0.55

was

0.55

Mis

0.54

 seemed

0.54

had

0.51

due

0.50

kla

0.50

Activations Density 0.245%

descriptive phrases related to visual appearances and technical details

No Comments

No Known Activations