INDEX

Explanations

general statements and qualifiers about trends or common practices

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

Followed by "if" or a comma

np_acts-logits-general · gemini-2.0-flash

generally, if

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Vidite

-0.83

 ―――――

-0.77

 ویکی‌پدی

-0.77

AISSEE

-0.75

AsUp

-0.75

 queſta

-0.74

TagMode

-0.74

 الرياضيه

-0.72

:✨

-0.69

 MainAxisSize

-0.67

POSITIVE LOGITS

 they

0.96

 there

0.96

we

0.91

it

0.81

0.79

he

0.64

there

0.63

they

0.62

you

0.60

she

0.56

Activations Density 0.481%

general statements and qualifiers about trends or common practices

Followed by "if" or a comma

generally, if

No Comments

No Known Activations