INDEX

Explanations

complex mathematical expressions and symbolic notation related to 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

-0.49

...

-0.47

-0.43

льф

-0.43

 that

-0.42

zin

-0.42

 Bennett

-0.42

POSITIVE LOGITS

 myſelf

1.07

 itſelf

1.06

 Houſe

1.04

 مشين

1.01

iNdEx

0.99

enumi

0.98

 kasarigan

0.96

 themſelves

0.94

 Anſ

0.94

 Jefus

0.92

Activations Density 0.742%

complex mathematical expressions and symbolic notation related to equations

No Comments

No Known Activations