INDEX

Explanations

positive attributes and superlatives related to various entities and experiences

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

Followed by "ever"

np_acts-logits-general · gemini-2.0-flash

superlative or extreme descriptions

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

ſelves

-0.92

 Jefus

-0.88

Efq

-0.88

Personendaten

-0.86

 myſelf

-0.85

 itſelf

-0.85

 }}$}

-0.85

 Forumite

-0.83

 initComponents

-0.81

ſelf

-0.81

POSITIVE LOGITS

 imaginable

0.79

 ever

0.78

 Ever

0.63

 possible

0.62

 EVER

0.57

Ever

0.57

0.55

we

0.54

 thing

0.53

ever

0.53

Activations Density 0.085%

positive attributes and superlatives related to various entities and experiences

Followed by "ever"

superlative or extreme descriptions

No Comments

No Known Activations