INDEX

Explanations

prepositions followed by a location or entity

oai_token-act-pair · gpt-3.5-turbo

instances of the preposition "in."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

EPA

-0.88

odor

-0.76

=]

-0.76

ICA

-0.75

ctors

-0.75

":["

-0.72

ĪĴ

-0.72

MAL

-0.72

Benz

-0.70

BILL

-0.70

POSITIVE LOGITS

built

0.81

tow

0.81

 handy

0.79

 ready

0.78

 abundance

0.73

 tight

0.71

clusions

0.70

 spare

0.69

 Lank

0.68

 locked

0.68

Activations Density 0.302%

prepositions followed by a location or entity

instances of the preposition "in."

No Comments

No Known Activations