INDEX

Explanations

phrases related to satisfaction and performance of products or services

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

Sentences ending with “and” or “i”

np_acts-logits-general · gemini-2.0-flash

overall, everything

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

 Vikipedi

-0.55

zheimer

-0.52

Hvem

-0.51

 Derfor

-0.51

ิลปะ

-0.50

 cualquiera

-0.50

 existi

-0.47

 solche

-0.47

 corporations

-0.46

 many

-0.45

POSITIVE LOGITS

 overall

1.06

overall

1.02

Overall

1.02

 Overall

1.00

 everything

0.93

Everything

0.89

everything

0.88

 Everything

0.88

一切都

0.81

OVERALL

0.80

Activations Density 0.179%

phrases related to satisfaction and performance of products or services

Sentences ending with “and” or “i”

overall, everything

No Comments

No Known Activations