INDEX

Explanations

words and phrases describing analysis and action, often in the scientific or academic realm.

oai_token-act-pair · gemini-2.0-flash

actions

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

IndentedString

-0.73

awtextra

-0.66

Enllaces

-0.66

 فريبيس

-0.65

bewerken

-0.63

findpost

-0.63

Anhalt

-0.63

"],

-0.63

toir

-0.62

exitRule

-0.61

POSITIVE LOGITS

 Galilee

0.59

 noastre

0.50

templateUrl

0.44

 jagung

0.43

 poffe

0.43

 quæ

0.43

 neceffary

0.42

 épis

0.42

rø

0.42

 fubject

0.42

Activations Density 12.829%

words and phrases describing analysis and action, often in the scientific or academic realm.

actions

No Comments

No Known Activations