INDEX

Explanations

instances of the word "marked" and related forms, indicating some form of identification or annotation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

ContentAsync

-0.81

katapos

-0.74

tenham

-0.69

polation

-0.69

 magát

-0.68

ChildScrollView

-0.68

 Heeren

-0.65

tetten

-0.64

氓

-0.63

zędu

-0.62

POSITIVE LOGITS

 marks

3.02

 mark

2.84

 Marks

2.66

 MARKS

2.65

marks

2.62

Marks

2.50

 marked

2.48

 marking

2.44

marked

2.39

mark

2.38

Activations Density 0.110%

instances of the word "marked" and related forms, indicating some form of identification or annotation

No Comments

No Known Activations