INDEX

Explanations

mentions of the word "emails"

oai_token-act-pair · gpt-3.5-turbo

mentions of emails

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

iasis

-0.75

axis

-0.74

stood

-0.70

 Glasgow

-0.68

GBT

-0.68

OV

-0.67

mbuds

-0.67

vic

-0.67

hood

-0.67

 Edinburgh

-0.66

POSITIVE LOGITS

 Emails

0.94

 inbox

0.91

 correspondence

0.88

 dumps

0.88

ileaks

0.88

 exchanged

0.85

 emails

0.85

 messages

0.82

 newsletters

0.82

archive

0.81

Activations Density 0.022%

mentions of the word "emails"

mentions of emails

No Comments

No Known Activations