INDEX

Explanations

instances of discourse markers or sentences that introduce or summarize key points

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

 تضيفلها

-0.79

WriteTagHelper

-0.72

AsUp

-0.70

tvguidetime

-0.70

 greateſt

-0.66



-0.66

RegressionTest

-0.64

الحياه

-0.64

 Anſ

-0.62

 feroit

-0.60

POSITIVE LOGITS

 actual

0.62

 thereof

0.54

それが

0.47

 them

0.46

>()

0.46

 dazu

0.46

 дописавши

0.43

fe

0.43

 actually

0.43

それを

0.42

Activations Density 0.450%

instances of discourse markers or sentences that introduce or summarize key points

No Comments

No Known Activations