INDEX

Explanations

terms related to structured patterns and configurations

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

InjectMocks

-0.60

ligan

-0.58

ทุน

-0.57

 miſ

-0.57

uxxxx

-0.54

 समीक्षक

-0.54

 uſed

-0.52

 fubject

-0.51

chemia

-0.51

تاح

-0.50

POSITIVE LOGITS

 stripes

0.78

 patterns

0.77

 spots

0.77

 pattern

0.72

pattern

0.68

 streaks

0.67

patterns

0.66

IUrlHelper

0.65

striping

0.65

縞

0.64

Activations Density 0.512%

terms related to structured patterns and configurations

No Comments

No Known Activations