INDEX

Explanations

the word "grade" when discussing academics

oai_token-act-pair · gemini-2.0-flash

grade

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 Monfieur

-1.17

 ainfi

-1.05

Efq

-1.05

 anſ

-0.98

 Theſe

-0.98

 enfans

-0.95

 raiſ

-0.94

 himſelf

-0.93

 Houſe

-0.92

 Majefty

-0.92

POSITIVE LOGITS

 […]

0.77

0.75

Mar

0.74

most

0.73

webElementXpaths

0.73

<eos>

0.73

0.71

NameInMap

0.69

<em>

0.69

Activations Density 1.629%

the word "grade" when discussing academics

grade

No Comments

No Known Activations