INDEX

Explanations

text from scientific publications

oai_token-act-pair · gemini-2.0-flash

system/bots

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 Kazim

-0.73

SPATH

-0.68

 AssemblyProduct

-0.67

 Shakspeare

-0.66

ResponseWriter

-0.65

bootstrapcdn

-0.63

LookAnd

-0.62

clearfix

-0.62

ViewFeatures

-0.62

 RSSSF

-0.62

POSITIVE LOGITS

bot

0.51

System

0.50

bot

0.47

amını

0.47

 realized

0.42

system

0.41

Bot

0.41

paddingVertical

0.40

sys

0.40

Bot

0.40

Activations Density 0.556%

text from scientific publications

system/bots

No Comments

No Known Activations