INDEX

Explanations

characters and symbols associated with web content and references

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ValueStyle

-0.73

gameserver

-0.69

 AssemblyCulture

-0.67

Abitanti

-0.66

 فريبيس

-0.63

 Anſ

-0.62

 AssemblyVersion

-0.59

참고

-0.57

IntoConstraints

-0.57

 ſtate

-0.54

POSITIVE LOGITS

__':

0.65

 للاسماء

0.56

✨:

0.54

How

0.52

‘

0.51

 Will

0.50

>');

0.49

<h1>

0.48

getDrawable

0.47

0.46

Activations Density 0.076%

characters and symbols associated with web content and references

No Comments

No Known Activations