INDEX

Explanations

references to authors or contributors and their affiliations in research or academic documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ſmall

-0.56

 spirit

-0.51

openqa

-0.49

 houſe

-0.49

TagMode

-0.49

lende

-0.48

 ends

-0.46

 Conſ

-0.46

OutputType

-0.46

 axes

-0.45

POSITIVE LOGITS

expandindo

0.69

tagHelperRunner

0.62

 estimés

0.59

jsii

0.57

 Савезне

0.56

saraba

0.56

تقاوى

0.56

évaluateur

0.55

arschu

0.55

حوالہ

0.54

Activations Density 0.500%

references to authors or contributors and their affiliations in research or academic documents

No Comments

No Known Activations