INDEX

Explanations

instances where something is observed or experienced directly

oai_token-act-pair · gpt-3.5-turbo

references to firsthand experiences and eyewitness accounts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

nan

-0.79

merce

-0.78

corn

-0.77

ramid

-0.77

nam

-0.71

rar

-0.71

rug

-0.69

uyomi

-0.67

erenn

-0.67

ishops

-0.66

POSITIVE LOGITS

 firsthand

1.16

ewitness

0.94

 eyewitness

0.81

Effects

0.73

 attest

0.69

 testimonies

0.68

 VIDEOS

0.66

 Explorer

0.64

 witness

0.62

 perspect

0.62

Activations Density 0.009%

instances where something is observed or experienced directly

references to firsthand experiences and eyewitness accounts

No Comments

No Known Activations