INDEX

Explanations

references to the word "there" or general references to blog posts.

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

MessageState

-0.69

-0.68

 ſtand

-0.68

 myſelf

-0.66

 whoſe

-0.63

 AssemblyCulture

-0.63

 itſelf

-0.61

 ModelExpression

-0.60

withIdentifier

-0.60

 againſt

-0.60

POSITIVE LOGITS

hasNext

0.44

انجليز

0.42

IUrlHelper

0.41

alnız

0.40

Xaml

0.40

 golongan

0.40

pat

0.40

CPtr

0.39

 Ersten

0.39

هرة

0.39

Activations Density 0.469%

references to the word "there" or general references to blog posts.

No Comments

No Known Activations