INDEX

Explanations

references to parts or portions of entities or systems

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

稀

-0.48

or

-0.47

-0.46

ზ

-0.44

↵

-0.43

递

-0.43

er

-0.43

’

-0.43

тари

-0.43

aj

-0.42

POSITIVE LOGITS

 betweenstory

1.29

 ProtoMessage

1.08

 portion

1.02

writeFieldEnd

0.97

InitVars

0.96

 चीज़ों

0.94

portion

0.94

 Portion

0.93

 initComponents

0.92

 part

0.91

Activations Density 0.468%

references to parts or portions of entities or systems

No Comments

No Known Activations