INDEX

Explanations

phrases indicating multiple instances or occurrences

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

oulos

-0.72

ocate

-0.68

lance

-0.67

brace

-0.66

Ì¶

-0.65

 Presence

-0.64

GGGGGGGG

-0.63

lio

-0.63

ammers

-0.63

robe

-0.62

POSITIVE LOGITS

 occasions

1.90

 occasion

1.60

 basis

1.34

 fronts

1.31

 behalf

1.25

 pretext

1.19

 grounds

1.13

 continents

1.08

 campuses

1.06

occ

0.95

Activations Density 0.171%

phrases indicating multiple instances or occurrences

No Comments

No Known Activations