INDEX

Explanations

prepositions used to indicate location or position

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "in"

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

llor

-0.71

Published

-0.67

-0.65

CLASSIFIED

-0.65

bryce

-0.61

catentry

-0.59

Continue

-0.58

 Advertisement

-0.58

CVE

-0.58

 lodged

-0.58

POSITIVE LOGITS

clus

1.28

 regards

1.26

 spite

1.21

animate

1.20

clusions

1.19

 lieu

1.16

ordinate

1.16

clusively

1.14

organic

1.14

roads

1.11

Activations Density 0.463%

prepositions used to indicate location or position

occurrences of the word "in"

No Comments

No Known Activations