INDEX

Explanations

mathematical expressions and symbols in equations

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

spo

-0.70

ma

-0.67

Moq

-0.58

esh

-0.56

dy

-0.55

spo

-0.55

dar

-0.55

rū

-0.55

str

-0.54

 Yama

-0.54

POSITIVE LOGITS

^{(

1.67

}^{(

1.54

}}^{(

1.51

}^{(\

1.36

 }^{(

1.29

^{(\

1.27

 itſelf

1.25

Efq

1.24

[[

1.17

[[

1.11

Activations Density 0.338%

mathematical expressions and symbols in equations

No Comments

No Known Activations