INDEX

Explanations

phrases related to conflicts, discussions, and orders

oai_token-act-pair · gpt-3.5-turbo

key terms associated with conflict or discussions of significant events

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

aciously

-0.62

advertisement

-0.59

 endif

-0.58

MpServer

-0.57

conservancy

-0.56

 Cosponsors

-0.56

inki

-0.56

"},"

-0.56

idi

-0.55

NOW

-0.54

POSITIVE LOGITS

0.88

 there

0.86

 they

0.73

we

0.73

,[

0.68

he

0.67

 nobody

0.65

it

0.64

,,

0.64

there

0.64

Activations Density 0.463%

phrases related to conflicts, discussions, and orders

key terms associated with conflict or discussions of significant events

No Comments

No Known Activations