INDEX

Explanations

descriptive phrases emphasizing the extent, range, or flexibility of something

oai_token-act-pair · gpt-3.5-turbo

concepts related to freedom and permissiveness in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 Photograph

-0.65

TPS

-0.65

 plaque

-0.64

AGA

-0.63

 badge

-0.63

iron

-0.60

acea

-0.60

 Mehran

-0.60

Mub

-0.60

lehem

-0.59

POSITIVE LOGITS

 possibilities

1.61

 flexibility

1.29

 customization

1.23

 options

1.22

 choices

1.21

 creativity

1.15

 freedom

1.11

 discretion

1.09

 versatility

1.08

 freedoms

1.08

Activations Density 0.509%

descriptive phrases emphasizing the extent, range, or flexibility of something

concepts related to freedom and permissiveness in various contexts

No Comments

No Known Activations