INDEX

Explanations

references to copyright and licensing information

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

<eos>

-0.60

GOTREF

-0.57

 […]

-0.52

AutoScale

-0.52

and

-0.48

 ProtoMessage

-0.48

 unknownFields

-0.47

’

-0.45

ModelAdmin

-0.43

localVar

-0.43

POSITIVE LOGITS

 Мексичка

0.87

 فريبيس

0.86

 estimés

0.83

expandindo

0.81

évaluateur

0.80

Hochspringen

0.79

!*\

0.78

 Réponses

0.78

 pleaſure

0.77

 تضيفلها

0.76

Activations Density 0.652%

references to copyright and licensing information

No Comments

No Known Activations