INDEX

Explanations

mentions of specific buildings, locations, and organizations

oai_token-act-pair · gpt-3.5-turbo

references to specific buildings and locations related to significant events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

emonic

-0.77

abase

-0.74

yip

-0.73

 snowball

-0.70

Ö¼

-0.66

enhagen

-0.66

vous

-0.66

azeera

-0.65

ramer

-0.65

zzy

-0.64

POSITIVE LOGITS

AMI

0.69

 Doors

0.69

bats

0.68

 Cemetery

0.67

Dialogue

0.67

 Gardens

0.65

 Fans

0.63

ople

0.63

 Meeting

0.63

 Walls

0.62

Activations Density 0.822%

mentions of specific buildings, locations, and organizations

references to specific buildings and locations related to significant events

No Comments

No Known Activations