INDEX

Explanations

programming-related terms and function definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

حوالہ

-0.58

 BrowserModule

-0.53

expandindo

-0.52

WireFormatLite

-0.50

 disponibilités

-0.49

#+#

-0.49

theatre

-0.47

IBarButtonItem

-0.47

̀n

-0.47

 ervan

-0.47

POSITIVE LOGITS

цездатний

0.58

:✨

0.54

isFunction

0.49

Перед

0.48

 Capricorn

0.48

stdarg

0.48

onAttach

0.48

ictus

0.48

 interpr

0.47

cony

0.46

Activations Density 0.401%

programming-related terms and function definitions

No Comments

No Known Activations