INDEX

Explanations

mentions of the word "Penn" with activation levels indicating the strongest match

oai_token-act-pair · gpt-3.5-turbo

mentions of "Penn" in various contexts related to institutions or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

++++++++++++++++

-0.71

________________________

-0.69

eer

-0.68

 balloons

-0.64

 Lumpur

-0.64

 Malays

-0.63

semble

-0.62

âĢķ

-0.62

 willful

-0.61

 immersion

-0.60

POSITIVE LOGITS

sylv

1.38

 Penn

1.27

Penn

1.21

sylvania

1.12

 Mellon

1.02

insula

0.93

erton

0.85

osuke

0.84

 Berks

0.83

essee

0.81

Activations Density 0.004%

mentions of the word "Penn" with activation levels indicating the strongest match

mentions of "Penn" in various contexts related to institutions or events

No Comments

No Known Activations