INDEX

Explanations

numerical data and lists that highlight key points or findings in a text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 linkovi

-0.60

contentLoaded

-0.60

adaptiveStyles

-0.58

يكب

-0.53

addGap

-0.53

ğlık

-0.52

jwa

-0.52

 considération

-0.51

protoimpl

-0.51

łop

-0.50

POSITIVE LOGITS

AndEndTag

0.65

tagHelperRunner

0.63

 myſelf

0.62

 einerseits

0.60

 Monfieur

0.59

 zufolge

0.56

medriver

0.56

0.55

esthetics

0.55

 Theſe

0.55

Activations Density 0.190%

numerical data and lists that highlight key points or findings in a text

No Comments

No Known Activations