INDEX

Explanations

prepositions and prepositional phrases that indicate a specific relationship between entities

oai_token-act-pair · gpt-3.5-turbo

prepositions and phrases indicating relationships or connections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Nir

-0.67

 Mages

-0.66

BuyableInstoreAndOnline

-0.65

 retard

-0.61

 blaze

-0.59

 bondage

-0.59

 Fundamental

-0.58

 Primordial

-0.58

 colony

-0.57

igor

-0.56

POSITIVE LOGITS

Ĭ±

0.86

rompt

0.81

appropriately

0.77

©¶æ

0.77

ivari

0.76

ĪĴ

0.76

direct

0.73

draft

0.72

¶ħ

0.72

nen

0.71

Activations Density 0.407%

prepositions and prepositional phrases that indicate a specific relationship between entities

prepositions and phrases indicating relationships or connections

No Comments

No Known Activations