INDEX

Explanations

the word 'hospitals'

oai_token-act-pair · gpt-4-turbo

words related to hospitals and healthcare providers

oai_token-act-pair · gpt-3.5-turbo

references to hospitals

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

uten

-0.63

estamp

-0.62

;;;;;;;;

-0.62

 Stronghold

-0.62

history

-0.61

âĢ¢âĢ¢âĢ¢âĢ¢

-0.61

BOOK

-0.60

 Ãĸ

-0.60

---------

-0.59

olitics

-0.59

POSITIVE LOGITS

itals

0.99

ilitating

0.90

 traged

0.89

 hospitals

0.89

 pharmacies

0.82

maid

0.79

chool

0.77

irtual

0.76

©¶æ

0.76

 tremend

0.75

Activations Density 0.014%

the word 'hospitals'

words related to hospitals and healthcare providers

references to hospitals

No Comments

No Known Activations