INDEX

Explanations

numbers and numerical data references within 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 @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 nakalista

-0.67

例句

-0.56

 chal

-0.52

 spieg

-0.52

chal

-0.52

timewa

-0.51

nię

-0.51

zionali

-0.49

ResponseEntity

-0.47

뜸

-0.46

POSITIVE LOGITS

setVerticalGroup

0.76

ViewFeatures

0.74

Datuak

0.68

 GetEnumerator

0.65

writeFieldEnd

0.65

ⓧ

0.63

 AssemblyTitle

0.63

ArrowToggle

0.63

oa̍t

0.62

writeField

0.62

Activations Density 0.212%

numbers and numerical data references within a text

No Comments

No Known Activations