INDEX

Explanations

mathematical notation that indicates mappings or functions, particularly in the context of subsets and transformations

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

/}{

-0.49

 setEmail

-0.49

^*)

-0.46

ური

-0.46

 ligiloj

-0.45

badah

-0.45

${

-0.45

 total

-0.44

pek

-0.44

bore

-0.44

POSITIVE LOGITS

rightarrow

2.33

longrightarrow

1.54

Rightarrow

1.38

→

1.29

→

1.20

mapsto

1.18

leftarrow

1.16

Leftrightarrow

1.11

➝

1.10



1.07

Activations Density 0.379%

mathematical notation that indicates mappings or functions, particularly in the context of subsets and transformations

No Comments

No Known Activations