INDEX

Explanations

phrases related to social or political debates and discussions

oai_token-act-pair · gpt-3.5-turbo

phrases that include conditional statements or implications

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

ļéĨĴ

-0.78

ãĤ´ãĥ³

-0.74

ãĤ¨ãĥ«

-0.73

VERTISEMENT

-0.72

Ě

-0.69

ğ

-0.69

quickShip

-0.69

Ė

-0.69

ē

-0.69

ă

-0.69

POSITIVE LOGITS

 then

1.36

then

1.27

 surely

1.21

why

1.19

 THEN

1.09

 chances

0.98

 maybe

0.98

why

0.96

 shouldn

0.93

 please

0.92

Activations Density 0.185%

phrases related to social or political debates and discussions

phrases that include conditional statements or implications

No Comments

No Known Activations