INDEX

Explanations

terms related to functions and methods in programming or code documentation

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

enumi

-0.98

 Italijanski

-0.89

KommentareTeilen

-0.88

 للمعارف

-0.85

MessageOf

-0.85

EDEFAULT

-0.83

:+:

-0.79

webElementXpaths

-0.79

IsContent

-0.79

 betweenstory

-0.78

POSITIVE LOGITS

an

0.54

for

0.54

 based

0.49

of

0.47

Lib

0.45

xue

0.44

the

0.43

 information

0.43

li

0.42

per

0.42

Activations Density 0.345%

terms related to functions and methods in programming or code documentation

No Comments

No Known Activations