INDEX

Explanations

terms related to dining or eating

oai_token-act-pair · gpt-3.5-turbo

references to dining experiences and related activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Archangel

-0.77

SON

-0.68

 Mehran

-0.67

ocus

-0.67

aments

-0.66

ku

-0.66

 Territories

-0.65

ukong

-0.65

-0.63

MAT

-0.63

POSITIVE LOGITS

 waiter

0.95

 lounge

0.92

 dining

0.88

 Guests

0.88

 patrons

0.85

 waitress

0.85

 guests

0.84

tainment

0.83

ounge

0.83

isure

0.83

Activations Density 0.091%

terms related to dining or eating

references to dining experiences and related activities

No Comments

No Known Activations