INDEX

Explanations

mentions of restaurants

oai_token-act-pair · gpt-3.5-turbo

mentions of restaurants

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

ioxide

-0.93

 spores

-0.73

vernment

-0.73

Downloadha

-0.72

izoph

-0.71

abee

-0.67

abies

-0.65

 Belarus

-0.65

SPD

-0.64

ucl

-0.64

POSITIVE LOGITS

 restaurants

1.12

 restaurant

1.08

 Restaur

1.07

 eater

1.01

 Restaurant

1.01

 chefs

0.99

 establishments

0.99

 chef

0.99

 menus

0.99

 waiter

0.91

Activations Density 0.037%

mentions of restaurants

mentions of restaurants

No Comments

No Known Activations