INDEX

Explanations

prepositions followed by a noun phrase

oai_token-act-pair · gpt-3.5-turbo

the preposition "in" appearing within the text

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

-0.56

NOW

-0.55

%%

-0.54

CLASSIFIED

-0.54

username

-0.51

 lodged

-0.50

killed

-0.48

âĿ

-0.47

HAEL

-0.47

casters

-0.45

POSITIVE LOGITS

 lieu

1.16

 accordance

1.13

 conjunction

1.08

ordinate

1.02

animate

1.00

clus

0.99

 vitro

0.99

 relation

0.97

clusions

0.97

 spite

0.96

Activations Density 0.603%

prepositions followed by a noun phrase

the preposition "in" appearing within the text

No Comments

No Known Activations