INDEX

Explanations

phrases or expressions indicating uncertainty or vague descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 armées

-0.55

 asla

-0.55

 unut

-0.54

 constexpr

-0.53

 vectorielle

-0.53

 quæ

-0.52

 africaine

-0.51

 contemporaine

-0.50

 exceedingly

-0.50

 absolutely

-0.50

POSITIVE LOGITS

 sorta

0.89

 unknownFields

0.83

Kinda

0.73

 متعلقه

0.71

 Kinda

0.70

kinda

0.68

FailureListener

0.67

 like

0.65

tagext

0.65

GroupLayout

0.64

Activations Density 0.155%

phrases or expressions indicating uncertainty or vague descriptions

No Comments

No Known Activations