INDEX

Explanations

prepositional phrases indicating causation or location

oai_token-act-pair · gpt-3.5-turbo

prepositions and their usage in sentences

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

Look

-0.36

—"

-0.33

sit

-0.33

No

-0.32

sylv

-0.32

ese

-0.32

å§

-0.32

 besides

-0.32

Like

-0.32

Attempt

-0.32

POSITIVE LOGITS

geries

0.46

 thee

0.44

 oneself

0.43

Rs

0.40

 Shutterstock

0.40

 infinity

0.37

 english

0.37

 debian

0.37

 facebook

0.36

 graphene

0.35

Activations Density 1.301%

prepositional phrases indicating causation or location

prepositions and their usage in sentences

No Comments

No Known Activations