INDEX

Explanations

words related to economic benefits or drawbacks, particularly in the context of social and political commentary

oai_token-act-pair · gpt-3.5-turbo

Triggered by @bot

words related to benefits or advantages, particularly in socio-economic contexts

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 12-res-jb

Configuration

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

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_post

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

body

-0.69

issues

-0.66

hew

-0.64

mess

-0.62

slice

-0.61

bles

-0.61

rez

-0.61

orders

-0.61

bender

-0.60

olver

-0.60

POSITIVE LOGITS

 enormously

1.29

 immensely

1.25

 greatly

1.24

 tremendously

1.18

 financially

1.14

 handsome

1.11

 hugely

1.08

 materially

1.01

 from

1.01

 disproportionately

0.99

Activations Density 0.087%

words related to economic benefits or drawbacks, particularly in the context of social and political commentary

words related to benefits or advantages, particularly in socio-economic contexts

No Known Activations