INDEX

Explanations

statements regarding the effectiveness of interventions or treatments

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

"effect"

np_acts-logits-general · gemini-2.0-flash

effect of

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

AccessFile

-0.80

ganu

-0.67

WriteBarrier

-0.66

findpost

-0.62

IBarButtonItem

-0.59

 BoxFit

-0.57

 allAfrica

-0.56

astify

-0.55

-0.54

ंदीखरीदारी

-0.53

POSITIVE LOGITS

 spéciaux

0.72

 fallu

0.67

 samping

0.67

 levier

0.65

 Effects

0.63

ingly

0.62

Eff

0.61

IVENESS

0.58

Effects

0.58

 couverte

0.58

Activations Density 0.145%

statements regarding the effectiveness of interventions or treatments

"effect"

effect of

No Comments

No Known Activations