INDEX

Explanations

terms related to documentation and purchasing processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

يج

-0.68

ge

-0.66

al

-0.66

 darn

-0.65

 kids

-0.63

нгредіє

-0.62

плек

-0.62

/***/

-0.61

éf

-0.61

POSITIVE LOGITS

#+#

0.85

jarat

0.79

 linkovi

0.79

····

0.78

مراجع

0.77

AddHtmlAttribute

0.75

⎓

0.75

othesis

0.74

}{*}{}

0.74

nologies

0.73

Activations Density 0.819%

terms related to documentation and purchasing processes

No Comments

No Known Activations