INDEX

Explanations

proper nouns related to organizations or locations

oai_token-act-pair · gpt-3.5-turbo

the term "United" or related phrases indicating a collective or organization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

\\\\\\\\\\\\\\\\

-0.72

MY

-0.70

ebook

-0.68

BOOK

-0.67

ovie

-0.67

beit

-0.66

CHR

-0.66

ouf

-0.65

 brim

-0.64

 Metatron

-0.64

POSITIVE LOGITS

 States

1.20

 Nations

1.19

 Airlines

1.04

 Methodist

1.04

 STATES

0.97

States

0.85

sburg

0.84

 Kingdom

0.81

 Federation

0.80

ications

0.76

Activations Density 0.031%

proper nouns related to organizations or locations

the term "United" or related phrases indicating a collective or organization

No Comments

No Known Activations