INDEX

Explanations

occurrences of the word "chef" or related words like "cuisine" or "pastry", often in connection with the White House.

oai_token-act-pair · gemini-2.0-flash

chefs and food

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

Muf

-0.50

 Orton

-0.50

Tē

-0.49

ícil

-0.46

 Engineering

-0.46

abaza

-0.45

 Mand

-0.44

eability

-0.44

hab

-0.44

 Lombardo

-0.44

POSITIVE LOGITS

webElementXpaths

0.74

WithIOException

0.74

findpost

0.71

TagMode

0.70

PerformLayout

0.69

LookAnd

0.66

 AssemblyTitle

0.62

istiques

0.60

setVerticalGroup

0.60

ValueStyle

0.59

Activations Density 3.265%

occurrences of the word "chef" or related words like "cuisine" or "pastry", often in connection with the White House.

chefs and food

No Comments

No Known Activations