INDEX

Explanations

instances where something is possessed or owned by someone

oai_token-act-pair · gpt-3.5-turbo

mentions of ownership or possession

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

 Bounty

-0.79

advertising

-0.69

 Cosponsors

-0.67

 Lauder

-0.66

 STATS

-0.66

Kov

-0.64

NESS

-0.62

:{

-0.62

ettings

-0.62

adj

-0.61

POSITIVE LOGITS

 repaired

0.77

iked

0.74

 haircut

0.73

ipolar

0.71

 chance

0.71

iphany

0.71

readable

0.70

 conversation

0.70

 impact

0.69

 rethink

0.69

Activations Density 0.357%

instances where something is possessed or owned by someone

mentions of ownership or possession

No Comments

No Known Activations