INDEX

Explanations

scientific terminology and structured data references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

dal

-0.44

Vil

-0.43

eam

-0.42

((

-0.42

</h3>

-0.42

</h2>

-0.42

-0.41

 Thomas

-0.40

лы

-0.40

POSITIVE LOGITS

 myſelf

1.08

 pleaſure

1.02

 itſelf

1.00

 Monfieur

0.98

 Jefus

0.97

 houſe

0.97

 purpoſe

0.95

Efq

0.95

 raiſ

0.95

ंदीखरीदारी

0.95

Activations Density 1.624%

scientific terminology and structured data references

No Comments

No Known Activations