INDEX

Explanations

keywords related to cafes

oai_token-act-pair · gpt-3.5-turbo

mentions of cafes and related dining establishments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

RAY

-0.84

ansom

-0.69

PATH

-0.69

Boh

-0.68

SON

-0.67

guided

-0.66

kus

-0.64

IGHTS

-0.64

odd

-0.64

ANG

-0.62

POSITIVE LOGITS

 cafe

1.53

 cafes

1.41

 Cafe

1.35

 cafÃ©

1.35

 CafÃ©

1.19

caf

1.17

eteria

0.99

 kios

0.97

 racer

0.96

 Restaurant

0.96

Activations Density 0.004%

keywords related to cafes

mentions of cafes and related dining establishments

No Comments

No Known Activations