INDEX

Explanations

references to smart technology/devices

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "smart" in various contexts

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

ĸļ

-0.80

hedral

-0.79

 Divinity

-0.78

 Syndrome

-0.75

UGE

-0.71

Reloaded

-0.70

alogue

-0.69

xual

-0.68

 Welch

-0.68

ICAN

-0.66

POSITIVE LOGITS

ctl

0.98

ness

0.92

ling

0.91

ening

0.86

ass

0.86

spot

0.85

matic

0.83

gest

0.83

watch

0.82

guy

0.82

Activations Density 0.030%

references to smart technology/devices

occurrences of the word "smart" in various contexts

No Comments

No Known Activations