INDEX

Explanations

references to specific hotels

oai_token-act-pair · gpt-3.5-turbo

mentions of hotels

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

*/(

-0.79

lang

-0.75

ebook

-0.73

unders

-0.69

tan

-0.69

sonian

-0.68

ranked

-0.66

eded

-0.65

 instr

-0.63

 literacy

-0.62

POSITIVE LOGITS

 Hotel

1.27

 Rooms

0.86

 Plaza

0.86

 Room

0.85

 Royale

0.83

ZI

0.82

 Club

0.81

 Suite

0.80

 Restaur

0.80

Hot

0.80

Activations Density 0.018%

references to specific hotels

mentions of hotels

No Comments

No Known Activations