INDEX

Explanations

references to figures and diagrams

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

references to figures or illustrations in the text

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

figure references and comparisons

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-65k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 link

-0.53

TabStop

-0.51

#+#

-0.50

Link

-0.49

 Link

-0.48

link

-0.46

Clik

-0.43

ģ

-0.43

 linker

-0.42

 habrá

-0.41

POSITIVE LOGITS

1.18

|}{$

1.00

}{$

0.78

0.71

SequentialGroup

0.68

Anhalt

0.65

*$

0.65

=>$

0.65

;$

0.65

Activations Density 0.818%

references to figures and diagrams

references to figures or illustrations in the text

figure references and comparisons

No Comments

No Known Activations