INDEX

Explanations

prepositions followed by a location or object

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "the"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

payers

-0.75

mania

-0.75

brate

-0.74

JUST

-0.71

olicy

-0.71

ulet

-0.70

blem

-0.64

NES

-0.64

APH

-0.63

ï¸ı

-0.63

POSITIVE LOGITS

 hallway

1.42

 doorway

1.29

 midst

1.27

 lobby

1.24

 courtyard

1.23

 driveway

1.20

 middle

1.20

 bathroom

1.17

 bushes

1.13

 woods

1.13

Activations Density 0.144%

prepositions followed by a location or object

occurrences of the word "the"

No Comments

No Known Activations