INDEX

Explanations

connections between variables in a scientific context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 utafitiHapana

-1.04

ReusableCell

-0.84

enumi

-0.80

+#+#

-0.77

 CreateTagHelper

-0.74

 Мексичка

-0.65

клопе

-0.63

EndContext

-0.62

runApp

-0.62

 للمعارف

-0.61

POSITIVE LOGITS

例文帳に追加

0.58

 <<<<<<<<<<<<<<

0.53

}}}}

0.51

</tr>

0.50

↵↵↵↵↵↵↵

0.48

ereich

0.47

↵↵↵↵↵

0.47

/}.

0.46

lied

0.45

Activations Density 1.085%

connections between variables in a scientific context

No Comments

No Known Activations