INDEX

Explanations

references to authors or authorship

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

The string "Author" followed by "itative"

np_acts-logits-general · gemini-2.0-flash

authoritative answers

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

 nahilalakip

-0.67

Mí

-0.65

 TextInputType

-0.62

AddTagHelper

-0.59

 betweenstory

-0.57

 LoginComponent

-0.55

ProgressHUD

-0.55

wic

-0.53

Nikki

-0.53

tire

-0.52

POSITIVE LOGITS

 CURIAM

0.76

itative

0.73

Authors

0.65

 uova

0.65

;"></

0.64

 authors

0.63

 PublicKey

0.60

 Authors

0.59

Hozzáférés

0.58

authors

0.58

Activations Density 0.123%

references to authors or authorship

The string "Author" followed by "itative"

authoritative answers

No Comments

No Known Activations