INDEX

Explanations

the word "latest" in various contexts, such as technology updates, news, and releases

oai_token-act-pair · gpt-3.5-turbo

references to current updates or news related to technology

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

erved

-0.87

alties

-0.86

avery

-0.78

dinand

-0.73

verning

-0.72

bos

-0.71

xual

-0.71

rahim

-0.71

hovah

-0.70

 Rahman

-0.70

POSITIVE LOGITS

 incarnation

1.08

 iteration

1.07

 installment

1.04

 edition

1.01

 update

0.95

 developments

0.95

 updates

0.90

 batch

0.86

 editions

0.85

 installments

0.82

Activations Density 0.021%

the word "latest" in various contexts, such as technology updates, news, and releases

references to current updates or news related to technology

No Comments

No Known Activations