INDEX

Explanations

instructions related to email formatting and etiquette

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

Follows "do not" or similar negation

np_acts-logits-general · gemini-2.0-flash

don't do anything too much

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

følgelig

-0.72

numerusform

-0.67

MessageOf

-0.63

yym

-0.61

الإنجليزية

-0.60

MessageTagHelper

-0.60

anggil

-0.59

ۜ

-0.57

enial

-0.56

CodedInputStream

-0.56

POSITIVE LOGITS

any

0.80

 anything

0.77

 terlalu

0.74

 unnecessarily

0.74

 unless

0.74

 слишком

0.70

 excessively

0.68

Any

0.67

too

0.67

ANY

0.67

Activations Density 0.345%

instructions related to email formatting and etiquette

Follows "do not" or similar negation

don't do anything too much

No Comments

No Known Activations