INDEX

Explanations

conjunctions and references to decision-making processes

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

Followed by "not" or a negative word

np_acts-logits-general · gemini-2.0-flash

not

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

WriteTagHelper

-0.61

ętr

-0.48

MENAFN

-0.47

TargetApi

-0.46

hasa

-0.46

ļas

-0.46

OrWhiteSpace

-0.45

RegisterType

-0.45

insee

-0.45

Życiorys

-0.45

POSITIVE LOGITS

not

3.65

not

3.03

Not

2.67

Not

2.57

NOT

2.48

NOT

2.44

 nicht

1.76

 bukan

1.72

 نه

1.67

 niet

1.61

Activations Density 1.041%

conjunctions and references to decision-making processes

Followed by "not" or a negative word

not

No Comments

No Known Activations