INDEX

Explanations

HTML tags and elements

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

HTML table code

np_acts-logits-general · gemini-2.0-flash

app descriptions and software features

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

 bois

-0.50

-0.47

DOCTYPE

-0.46

یز

-0.43

ItemGroup

-0.42

tilo

-0.42

doctype

-0.42

usammen

-0.42

-0.41

adis

-0.41

POSITIVE LOGITS

 Tade

0.65

✭✭

0.64

 تضيفلها

0.63

orari

0.61

 Sampler

0.61

BufferException

0.59

 المعيارى

0.58

wahati

0.57

Efq

0.56

thâu

0.56

Activations Density 0.019%

HTML tags and elements

HTML table code

app descriptions and software features

No Comments

No Known Activations