INDEX

Explanations

symbols and mathematical notation

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

Math mode environments

np_acts-logits-general · gemini-2.0-flash

angle brackets and parentheses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

########.

-0.65

-0.64

 Roskov

-0.60

 faſt

-0.57

 pleaſure

-0.52

 giusti

-0.51

 "..\..\..\

-0.50

 itſelf

-0.49

 Савезне

-0.47

 myſelf

-0.47

POSITIVE LOGITS

buttonShape

0.68

0.64

醐

0.62

endcsname

0.62

UrlResolution

0.62

impianto

0.62

embang

0.62

Vanjske

0.61

ViewFeatures

0.61

WEBPACK

0.61

Activations Density 0.035%

symbols and mathematical notation

Math mode environments

angle brackets and parentheses

No Comments

No Known Activations