INDEX

Explanations

terms associated with mathematical and logical reasoning

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

AutoScaleMode

-0.48

 }}">

-0.47

})),

-0.47

 EnglishChoose

-0.46

DataAnnotations

-0.45

TagHelper

-0.45

),”

-0.44

:].

-0.44

}}],

-0.42

",{

-0.42

POSITIVE LOGITS

ỡng

0.72

 تضيفلها

0.67

 незавершена

0.64

thâu

0.64

المناصب

0.64

__(/*!

0.63

LookAnd

0.62

CLUYE

0.59

 nahilalakip

0.59

 ddelweddau

0.58

Activations Density 0.984%

terms associated with mathematical and logical reasoning

No Comments

No Known Activations