INDEX

Explanations

terms related to official nominations or entries for awards

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

Protos

-0.54

ocardio

-0.46

 Rund

-0.46

 touché

-0.44

 الأح

-0.42

 turbin

-0.41

Sk

-0.41

 Pathol

-0.41

 constriction

-0.41

tedì

-0.41

POSITIVE LOGITS

 representative

1.39

 representation

1.36

Represent

1.31

 represent

1.29

 representing

1.26

 Representing

1.26

represent

1.25

 Representation

1.25

 REPRESENT

1.25

 Represent

1.24

Activations Density 0.236%

terms related to official nominations or entries for awards

No Comments

No Known Activations