INDEX

Explanations

mathematical symbols and notations related to equations and inequalities

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

Mathematical or code comparisons using greater/less than

np_acts-logits-general · gemini-2.0-flash

comparison involving less than or greater than

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

SourceChecksum

-0.58

InitVars

-0.56

 ***!

-0.53

 мәкалә

-0.53

Equ

-0.51

хьтан

-0.50

 getItemId

-0.50

equ

-0.49

ContentAlignment

-0.49

sizeCache

-0.48

POSITIVE LOGITS

1.44

1.24

1.23

$>

1.18

$<

1.17

 exceeds

1.17

$<$

1.16

1.12

 exceed

1.12

Activations Density 1.201%

mathematical symbols and notations related to equations and inequalities

Mathematical or code comparisons using greater/less than

comparison involving less than or greater than

No Comments

No Known Activations