INDEX

Explanations

negations and expressions related to denial or absence

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

็จ

-0.62

 adentro

-0.56

 invece

-0.56

 instead

-0.55

żeń

-0.54

 Instead

-0.54

aphone

-0.52

Instead

-0.52

ябрь

-0.51

AndEndTag

-0.51

POSITIVE LOGITS

CGContext

0.62

MigrationBuilder

0.60

PreferredItem

0.59

ſo

0.58

 purpoſe

0.58

 équ

0.56

省市镇

0.56

 ſel

0.56

findpost

0.55

FontStyle

0.55

Activations Density 0.237%

negations and expressions related to denial or absence

No Comments

No Known Activations