INDEX

Explanations

negations and words that may be part of other languages (not English).

oai_token-act-pair · gemini-2.0-flash

negations or the concept of absence

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

negation

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 already

-0.52

zköz

-0.44

 вже

-0.44

 bereits

-0.43

nsic

-0.43

 Already

-0.43

Not

-0.41

zések

-0.41

 Ikke

-0.41

itance

-0.41

POSITIVE LOGITS

parsedMessage

0.81

ValueStyle

0.74

WindowConstants

0.73

 linkovi

0.72

 initComponents

0.68

 Wicidata

0.68

WriteBarrier

0.67

GOTREF

0.67

afficheront

0.67

>{@

0.66

Activations Density 0.308%

negations and words that may be part of other languages (not English).

negations or the concept of absence

negation

No Comments

No Known Activations