INDEX

Explanations

occurrences of specific entities related to collections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

rehensible

-0.50

ExecuteReader

-0.49

 مشين

-0.49

">—

-0.49

awaiter

-0.47

koz

-0.46

chooser

-0.45

gnac

-0.44

PyExc

-0.43

Портал

-0.43

POSITIVE LOGITS

 located

1.54

 resides

1.40

 residing

1.33

 reside

1.30

 housed

1.29

located

1.24

 Located

1.20

 situated

1.19

 berada

1.17

 resided

1.16

Activations Density 0.698%

occurrences of specific entities related to collections

No Comments

No Known Activations