INDEX

Explanations

references to specific seasons of a show

oai_token-act-pair · gpt-3.5-turbo

references to different seasons of a series or show

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

hai

-0.76

istani

-0.71

rag

-0.70

mercial

-0.68

enei

-0.68

 sten

-0.67

 plugged

-0.65

berman

-0.63

gery

-0.63

inburgh

-0.62

POSITIVE LOGITS

 finale

1.04

 premiere

0.94

 opener

0.91

 Premiere

0.74

ally

0.71

 premie

0.70

ç¥ŀ

0.69

ticket

0.68

 Ticket

0.67

ç«

0.66

Activations Density 0.037%

references to specific seasons of a show

references to different seasons of a series or show

No Comments

No Known Activations