INDEX

Explanations

time durations expressed in years

oai_token-act-pair · gpt-3.5-turbo

the word "nearly" and its variations to indicate approximate quantities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

agate

-0.93

oris

-0.73

 locality

-0.70

":[

-0.68

DH

-0.68

oran

-0.66

 messenger

-0.64

ysis

-0.64

 Provision

-0.63

arella

-0.62

POSITIVE LOGITS

 identical

0.79

 tripled

0.71

ceed

0.69

stress

0.68

0.67

utherford

0.67

PsyNetMessage

0.66

 doubled

0.65

iannopoulos

0.65

Activations Density 0.038%

time durations expressed in years

the word "nearly" and its variations to indicate approximate quantities

No Comments

No Known Activations