INDEX

Explanations

negatives compared to alternative situations or outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

mybatisplus

-0.57

 ngan

-0.49

iphery

-0.45

rem

-0.45

mayr

-0.45

onite

-0.44

ništ

-0.43

rootDir

-0.43

SizeF

-0.43

tổng

-0.42

POSITIVE LOGITS

:✨

0.69

tvguidetime

0.63

 CURIAM

0.59

PerformLayout

0.57

ValueStyle

0.57

 Houſe

0.56

 "..\..\..\

0.56

NewRow

0.56

 Jefus

0.55

endphp

0.55

Activations Density 0.288%

negatives compared to alternative situations or outcomes

No Comments

No Known Activations