INDEX

Explanations

phrases related to research processes and outcomes

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

"at the" followed by a level

np_acts-logits-general · gemini-2.0-flash

levels and scale

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

aarrggbb

-0.67

parsedMessage

-0.62

Referanser

-0.61

AndEndTag

-0.60

doub

-0.56

oneofs

-0.50

 lệ

-0.49

 agrí

-0.49

ounid

-0.49

 defaultstate

-0.49

POSITIVE LOGITS

 macro

0.83

 granular

0.76

 grassroots

0.75

 individual

0.73

 macroscopic

0.69

macro

0.69

 operational

0.67

 institutional

0.65

 broadest

0.64

 micro

0.64

Activations Density 0.219%

phrases related to research processes and outcomes

"at the" followed by a level

levels and scale

No Comments

No Known Activations

phrases related to research processes and outcomes

"at the" followed by a level

levels and scale

No Comments

No Known Activations