INDEX

Explanations

references to specific individuals in relation to events or relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

PreferredItem

-0.78

complexType

-0.67

swire

-0.60

ವು

-0.60

simpleType

-0.60

UserScript

-0.57

apunov

-0.57

RectangleBorder

-0.57

ellyn

-0.57

 Chwiliwch

-0.57

POSITIVE LOGITS

 pasangan

0.73

 married

0.73

我和

0.71

 brothers

0.69

married

0.69

 супру

0.68

Married

0.67

 marié

0.67

 predeceased

0.66

你和

0.65

Activations Density 0.197%

references to specific individuals in relation to events or relationships

No Comments

No Known Activations