INDEX

Explanations

references to individuals or groups, particularly in a context of criticism or blame

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

Followed by a capitalized word

np_acts-logits-general · gemini-2.0-flash

initial word in a list item

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

Geplaatst

-0.79

 geslacht

-0.76

Diwedd

-0.71

Obrázky

-0.69

AnchorStyles

-0.67

Vidite

-0.65

Hochspringen

-0.64

 MainAxisSize

-0.64

Przypisy

-0.64

Tazama

-0.63

POSITIVE LOGITS

 المعيارى

0.76

SupportActionBar

0.71

medriver

0.70

ConstraintMaker

0.67

🏾

0.64

 ainfi

0.63

 ſtate

0.63

 المعرف

0.62

первых

0.61

 produisons

0.61

Activations Density 2.663%

references to individuals or groups, particularly in a context of criticism or blame

Followed by a capitalized word

initial word in a list item

No Comments

No Known Activations

references to individuals or groups, particularly in a context of criticism or blame

Followed by a capitalized word

initial word in a list item

No Comments

No Known Activations