INDEX

Explanations

elements that identify sources of information and artistic representation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

InSection

-0.68

 StatelessWidget

-0.61

motic

-0.61

 Roskov

-0.58

Iden

-0.58

 transfieras

-0.57

出版年

-0.57

IsMutable

-0.56

MetaObject

-0.55

öße

-0.54

POSITIVE LOGITS

 שוליים

0.60

 chiefly

0.59

=$?

0.58

Mainly

0.58

 insuffisamment

0.57

 mainly

0.56

primarily

0.55

 mehrerer

0.55

 mostly

0.54

 teils

0.54

Activations Density 0.570%

elements that identify sources of information and artistic representation

No Comments

No Known Activations