INDEX

Explanations

references to a specific protein or gene denoted by "Tre."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

bootstrapcdn

-0.75

Efq

-0.73

ConstraintMaker

-0.72

 ***!

-0.70

ariste

-0.69

MethodManager

-0.69

ValueStyle

-0.69

 Monfieur

-0.69

 contextLoads

-0.68

 Jefus

-0.67

POSITIVE LOGITS

Tre

0.94

tre

0.86

Tre

0.83

TRE

0.77

TRE

0.63

tre

0.60

Trev

0.58

 treat

0.51

Treating

0.50

 Trem

0.49

Activations Density 0.041%

references to a specific protein or gene denoted by "Tre."

No Comments

No Known Activations