INDEX

Explanations

organizations or entities that are responsible for various tasks or functions

oai_token-act-pair · gpt-3.5-turbo

phrases related to accountability and responsibility 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

iverse

-0.83

quickShipAvailable

-0.80

lass

-0.79

cipled

-0.77

osponsors

-0.75

SPONSORED

-0.74

Frag

-0.72

Times

-0.72

milo

-0.69

Instead

-0.68

POSITIVE LOGITS

 overseeing

1.75

 administering

1.47

 coordinating

1.45

 enforcing

1.41

 regulating

1.35

 managing

1.33

 handling

1.30

 guarding

1.28

 maintaining

1.27

 interpreting

1.26

Activations Density 0.204%

organizations or entities that are responsible for various tasks or functions

phrases related to accountability and responsibility in various contexts

No Comments

No Known Activations