INDEX

Explanations

keywords related to health and well-being 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

 hindurch

-0.47

miyorum

-0.45

Confusion

-0.45

 zufolge

-0.43

 Kitts

-0.41

 myself

-0.41

jeno

-0.40

totalPage

-0.39

onaceous

-0.39

putable

-0.39

POSITIVE LOGITS

IntoConstraints

0.99

SequentialGroup

0.89

 Meksiku

0.83

IndentedString

0.82

MessageOf

0.79

 ostavi

0.78

ApiModel

0.77

DoubleQuotes

0.77

 Мексичка

0.76

 Италијани

0.76

Activations Density 0.393%

keywords related to health and well-being concepts

No Comments

No Known Activations