INDEX

Explanations

verb "to be"

np_max-act-logits · gemini-2.0-flash

sentences containing the word 'is' or 'are', especially followed by a preposition or conditional

oai_token-act-pair · gemini-2.0-flash

meaningless

np_token-act-pair-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 виправивши

-0.58

HandlerContext

-0.57

expandindo

-0.55

reportWebVitals

-0.54

choso

-0.52

Nuorodos

-0.52

Loose

-0.52

getManager

-0.51

subpackage

-0.51

 OMITBAD

-0.51

POSITIVE LOGITS

setVerticalGroup

0.65

CodeAttribute

0.57

ITERIA

0.51

Mockito

0.50

 AssemblyProduct

0.46

mones

0.45

 ivelany

0.44

 setia

0.44

fit

0.44

 disbursed

0.43

Activations Density 4.006%

verb "to be"

sentences containing the word 'is' or 'are', especially followed by a preposition or conditional

meaningless

No Comments

No Known Activations