INDEX

Explanations

words related to lunar topics, baseball teams and medical terminology

oai_token-act-pair · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 vapours

-0.49

tcl

-0.49

Sib

-0.48

alde

-0.48

endphp

-0.47

ampu

-0.47

firi

-0.47

bero

-0.47

titu

-0.47

eax

-0.47

POSITIVE LOGITS

 مشين

0.73

 مرئيه

0.70

jadinya

0.67

IndentedString

0.65

ArrowToggle

0.64

хьтан

0.60

зулта

0.58

 Reverso

0.55

RegressionTest

0.54

 }}"></

0.54

Activations Density 3.407%

words related to lunar topics, baseball teams and medical terminology

No Comments

No Known Activations