INDEX

Explanations

references to actions or tasks that can be done in various contexts

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

Action or inaction regarding a problem

np_acts-logits-general · gemini-2.0-flash

doing about it

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

 mulighed

-0.46

 scattata

-0.45

 MyApp

-0.44

 heapq

-0.44

DataContract

-0.43

 scolaires

-0.43

æn

-0.42

ÈRE

-0.42

 toepassing

-0.41

ginfo

-0.41

POSITIVE LOGITS

 wrong

1.13

 differently

0.95

wrong

0.92

enumii

0.82

 Wrong

0.77

interopRequire

0.75

 WRONG

0.73

enterOuterAlt

0.72

 proactively

0.71

ActionCreators

0.69

Activations Density 0.145%

references to actions or tasks that can be done in various contexts

Action or inaction regarding a problem

doing about it

No Comments

No Known Activations