INDEX

Explanations

programming-related functions and methods

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

eradish

-0.48

nodeValue

-0.47

>[]

-0.43

 tòa

-0.42

 clone

-0.42

бин

-0.42

([])

-0.42

uomo

-0.41

뀜

-0.41

 subter

-0.40

POSITIVE LOGITS

NameInMap

1.40

SuppressMessage

0.99

mybatisplus

0.96

SuppressLint

0.95

PositiveButton

0.95

NegativeButton

0.94

featureID

0.93

addCriterion

0.92

「

0.91

mappedBy

0.91

Activations Density 0.151%

programming-related functions and methods

No Comments

No Known Activations