INDEX

Explanations

patterns indicating the start of new sections or paragraphs in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

StoryboardSegue

-0.77

AndEndTag

-0.76

RenderAtEndOf

-0.75

 CreateTagHelper

-0.74

 WebDriverWait

-0.69

DockStyle

-0.66

 BorderRadius

-0.65

 HttpNotFound

-0.64

WebControls

-0.64

awtextra

-0.63

POSITIVE LOGITS

دانشنامهٔ

0.54

lofen

0.52

تقاوى

0.52

sert

0.51

 drier

0.51

FEN

0.51

Hauptartikel

0.49

gars

0.49

維

0.48

eare

0.48

Activations Density 0.071%

patterns indicating the start of new sections or paragraphs in the text

No Comments

No Known Activations