INDEX

Explanations

mathematical expressions and formulas in the text

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

entailed formulas

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.16.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

-0.47

ਦ

-0.40

Tapped

-0.39

asset

-0.39

 kỳ

-0.38

年

-0.38

ave

-0.37

班

-0.36

enge

-0.35

Calculated

-0.35

POSITIVE LOGITS

RenderAtEndOf

1.14

tagHelperRunner

1.06

 Normdatei

1.06

ftagPool

1.05

 '\\;'

1.00

 betweenstory

0.98

########.

0.97

AndEndTag

0.96

 snippetHide

0.94

 utafitiHapana

0.94

Activations Density 0.653%

mathematical expressions and formulas in the text

entailed formulas

No Comments

No Known Activations