INDEX

Explanations

instances of the word "family" or words that collocate strongly with "family"

oai_token-act-pair · gemini-2.0-flash

non-English terms or foreign text

np_token-act-pair-logits · gpt-4o-mini

say "family"

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 onAnimation

-0.55

rahat

-0.49

 distanciation

-0.48

queryInterface

-0.47

positi

-0.46

 JpaRepository

-0.46

paraíso

-0.45

 quantum

-0.44

ividu

-0.44

rosine

-0.43

POSITIVE LOGITS

зулта

0.65

 >=",

0.64

 gynhyrchwyd

0.64

ConverterFactory

0.60

 المعيارى

0.59

SPATH

0.59

 autorytatywna

0.58

BeginContext

0.57

roix

0.55

 ویکی‌پدیای

0.54

Activations Density 2.718%

instances of the word "family" or words that collocate strongly with "family"

non-English terms or foreign text

say "family"

No Comments

No Known Activations