INDEX

Explanations

mathematical operations and expressions related to simplification and differentiation

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

Assumptions about variable signs (positive/prime)

np_acts-logits-general · gemini-2.0-flash

mathematical problem solving

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

TagMode

-1.13

 CreateTagHelper

-0.99

 незавершена

-0.93

BeginInit

-0.93

ReusableCell

-0.92

DockStyle

-0.89

uxxxx

-0.89

 ویکی‌پدیا

-0.87

 Normdatei

-0.84

parsedMessage

-0.84

POSITIVE LOGITS

</b>

0.71

 latter

0.55

<i>

0.51

``

0.51

ுக்கு

0.50

ace

0.47

)();

0.45

ніципа

0.45

чу

0.45

)()

0.44

Activations Density 2.569%

mathematical operations and expressions related to simplification and differentiation

Assumptions about variable signs (positive/prime)

mathematical problem solving

No Comments

No Known Activations