INDEX

Explanations

words related to communication or speech

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 Flickr

-0.70

mentation

-0.68

Mania

-0.65

 Folder

-0.63

 photograp

-0.62

mania

-0.61

 Judicial

-0.61

 encl

-0.61

 Wikimedia

-0.61

essors

-0.61

POSITIVE LOGITS

 truths

1.25

 words

1.16

 phrases

1.07

 aloud

1.04

 goodbye

1.01

word

0.97

 mantra

0.97

 prayers

0.96

 slogans

0.95

 pertinent

0.94

Activations Density 0.351%

words related to communication or speech

No Comments

No Known Activations