INDEX

Explanations

phrases related to epic storytelling and dramatic scenarios

oai_token-act-pair · gpt-3.5-turbo

punctuation marks, particularly periods and exclamation points

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

lier

-0.72

 biological

-0.71

pse

-0.70

ãĤ¶

-0.68

bole

-0.67

atism

-0.65

umably

-0.64

rys

-0.64

 depreciation

-0.63

acket

-0.62

POSITIVE LOGITS

 Featuring

1.41

 Additionally

1.32

 Lastly

1.18

 Along

1.16

 Meanwhile

1.10

 Includes

1.10

 Each

1.08

 Furthermore

1.07

 Whether

1.07

 Highlights

1.07

Activations Density 0.368%

phrases related to epic storytelling and dramatic scenarios

punctuation marks, particularly periods and exclamation points

No Comments

No Known Activations