INDEX

Explanations

references to quantitative research findings and the relationships among different data points or variables

oai_token-act-pair · gpt-4o-mini Triggered by @bot

followed by prepositions

np_acts-logits-general · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

Pro

-0.46

-0.44

<eos>

-0.42

Pro

-0.41

En

-0.41

an

-0.41

-0.40

Em

-0.40

POSITIVE LOGITS

same

1.61

 identical

1.43

Same

1.42

identical

1.37

 same

1.36

 desselben

1.35

 Same

1.34

SAME

1.29

 hetzelfde

1.25

 dezelfde

1.24

Activations Density 0.791%

references to quantitative research findings and the relationships among different data points or variables

followed by prepositions

same or similar

No Comments

No Known Activations