INDEX

Explanations

references to links or examples in text

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

Followed by: "Here's", "Here is", or "Here's an"

np_acts-logits-general · gemini-2.0-flash

Here's an introduction

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

 Meksiku

-0.89

TagMode

-0.83

 '\\;'

-0.81

Personensuche

-0.79

ThroughAttribute

-0.78

 Réponses

-0.75

 gynhyrchwyd

-0.73

الدراسه

-0.71

GTCX

-0.70

medriver

-0.69

POSITIVE LOGITS

 some

0.60

 what

0.59

 another

0.58

the

0.54

0.52

niz

0.49

naked

0.47

our

0.46

why

0.45

 naked

0.45

Activations Density 0.170%

references to links or examples in text

Followed by: "Here's", "Here is", or "Here's an"

Here's an introduction

No Comments

No Known Activations