INDEX

Explanations

verbs of ability or possibility, and prepositions.

oai_token-act-pair · gemini-2.0-flash

can/to

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

出版年

-0.86

 وتسجيلات

-0.84

 Jefus

-0.81

 Majefty

-0.77

ſelf

-0.71

 Lordships

-0.66

WriteBarrier

-0.66

ſelves

-0.65

 ComVisible

-0.65

PreExecute

-0.64

POSITIVE LOGITS

ParallelGroup

0.60

 SqlConnection

0.46

alo

0.45

jar

0.41

StackNavigator

0.41

 account

0.41

Xylene

0.41

ospital

0.40

 handle

0.40

oupe

0.40

Activations Density 1.090%

verbs of ability or possibility, and prepositions.

can/to

No Comments

No Known Activations