INDEX

Explanations

phrases related to conditions and situations indicating presence or absence of specific attributes and effectiveness of methods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

 AssemblyCulture

-1.10

 мәкал

-0.86

 nahilalakip

-0.79

 Theſe

-0.79

 myſelf

-0.78

 themſelves

-0.76

 betweenstory

-0.73

HtmlAttribute

-0.73

 Paglinawan

-0.72

ſy

-0.72

POSITIVE LOGITS

iv

0.47

šem

0.45

node

0.45

’

0.45

..

0.44

<eos>

0.44

..

0.42

com

0.42

直

0.42

Activations Density 0.810%

phrases related to conditions and situations indicating presence or absence of specific attributes and effectiveness of methods

No Comments

No Known Activations