INDEX

Explanations

mathematical expressions and symbols used 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 @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

<eos>

-1.26

↵↵

-1.26

-0.89

-0.87

↵↵↵

-0.83

\\

-0.80

-0.75

\\

-0.74

↵

-0.74

↵↵↵↵

-0.74

POSITIVE LOGITS

ſelf

1.22

 itſelf

1.18

NUMX

1.17

 myſelf

1.15

Efq

1.15

 houſe

1.12

出版年

1.10

neſs

1.09

 InputDecoration

1.05

 ſtate

1.05

Activations Density 0.957%

mathematical expressions and symbols used in equations

No Comments

No Known Activations