INDEX

Explanations

references to relationships and connections between concepts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ⓘ

-0.62

HomeAsUpEnabled

-0.62

astéro

-0.54

Personendaten

-0.53

CodeAttribute

-0.53

 Topping

-0.52

Décès

-0.52

ագրություններ

-0.52

tersebut

-0.51

POSITIVE LOGITS

abestanden

0.61

parsedMessage

0.53

 ddelweddau

0.50

///</

0.49

<table>

0.48

ArrowToggle

0.48

 transfieras

0.48

зова

0.46

 betweenstory

0.46

ModelAdmin

0.46

Activations Density 0.235%

references to relationships and connections between concepts

No Comments

No Known Activations