INDEX

Explanations

terms related to discussions or conversations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

googleapis

-0.63

 Zink

-0.62

whelmed

-0.59

колеп

-0.59

 plomb

-0.57

>>>>>>>>

-0.57

vindo

-0.56

 Borden

-0.55

PROVIDER

-0.55

$|\

-0.55

POSITIVE LOGITS

 discus

1.55

 discussion

1.51

 discuss

1.49

 Discuss

1.44

 discussing

1.36

 discussions

1.35

 discusses

1.35

discussion

1.34

 Discussions

1.30

 Discus

1.30

Activations Density 0.072%

terms related to discussions or conversations

No Comments

No Known Activations