INDEX

Explanations

numerical data or values

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

Citations with square brackets and the @ symbol

np_acts-logits-general · gemini-2.0-flash

citations and references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

+#+

-0.82

 initComponents

-0.82

UnusedPrivate

-0.73

NameInMap

-0.71

+#+#

-0.70

下载附件

-0.68

makeConstraints

-0.68

 مشين

-0.66

AnchorTagHelper

-0.66

 createState

-0.65

POSITIVE LOGITS

0.47

izr

0.46

 Walkover

0.45

0.42

imy

0.42

іга

0.41

ğinde

0.41

Hons

0.40

 보고

0.38

findall

0.38

Activations Density 0.150%

numerical data or values

Citations with square brackets and the @ symbol

citations and references

No Comments

No Known Activations