INDEX

Explanations

words related to cooking, sewing, or patterns, and the context those words appear in

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

IsContent

-0.82

 المعيارى

-0.82

 pleaſure

-0.72



-0.68

ModelAdmin

-0.68

ScopeManager

-0.66

 NSCoder

-0.65

 CURIAM

-0.65

DotNetBar

-0.64

ništvo

-0.63

POSITIVE LOGITS

<bos>

0.54

bed

0.50

Bed

0.49

Rüyada

0.47

 cover

0.44

************/

0.44

"){

0.43

ca

0.43

--){

0.43

BED

0.42

Activations Density 1.226%

words related to cooking, sewing, or patterns, and the context those words appear in

No Comments

No Known Activations