INDEX

Explanations

questions and queries related to systems and decision-making processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 ProtoMessage

-0.66

Personensuche

-0.66

Хьажоргаш

-0.59

InvalidProtocol

-0.56

 '\\;'

-0.56

 Wikimedijinoj

-0.55

انجليز

-0.52

 henvisninger

-0.51

 AssemblyVersion

-0.51

@[+][

-0.51

POSITIVE LOGITS

 fine

1.93

OK

1.62

 okay

1.62

Fine

1.61

fine

1.60

 Fine

1.56

ok

1.55

 FINE

1.53

 alright

1.45

OK

1.35

Activations Density 0.233%

questions and queries related to systems and decision-making processes

No Comments

No Known Activations