INDEX

Explanations

names or identities mentioned in the text, particularly when they are listed or referred to in a specific context

oai_token-act-pair · gpt-3.5-turbo

occurrences and related discussions of names

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

Synopsis

-0.70

BUG

-0.67

Delivery

-0.67

Britain

-0.62

Args

-0.61

Attempts

-0.61

Hur

-0.59

 gratitude

-0.59

rius

-0.59

 Marriott

-0.59

POSITIVE LOGITS

paces

1.86

pace

1.55

etting

1.39

hips

1.32

etter

1.27

poons

1.26

hip

1.23

peed

1.23

mith

1.22

creen

1.20

Activations Density 0.189%

names or identities mentioned in the text, particularly when they are listed or referred to in a specific context

occurrences and related discussions of names

No Comments

No Known Activations