INDEX

Explanations

patterns related to structure and declarations in programming code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/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.21.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

NameInMap

-0.61

WidgetItem

-0.55

cshtml

-0.54

:✨

-0.52

 Appellee

-0.52

 متعلقه

-0.50

ChildIndex

-0.50

 Eilish

-0.50

dispatch

-0.48

 trajets

-0.47

POSITIVE LOGITS

 تضيفلها

0.64

 référence

0.57

ums

0.57

state

0.54

 state

0.53

GHIJKLM

0.52

Refs

0.52

vernote

0.51

NOPQRST

0.50

Ump

0.50

Activations Density 0.058%

patterns related to structure and declarations in programming code

No Comments

No Known Activations