INDEX

Explanations

names 'Kra' and 'Barrett'

oai_token-act-pair · gpt-3.5-turbo

names of people and brands

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

istics

-0.89

loo

-0.87

abases

-0.80

arette

-0.79

isphere

-0.78

iates

-0.75

atta

-0.75

istrate

-0.75

estones

-0.74

bledon

-0.73

POSITIVE LOGITS

 Canaver

0.90

hovah

0.82

 Whedon

0.73

 Bulg

0.72

leck

0.70

terday

0.69

destruct

0.68

Boe

0.66

erenn

0.66

 Braun

0.65

Activations Density 0.069%

names 'Kra' and 'Barrett'

names of people and brands

No Comments

No Known Activations