INDEX

Explanations

references to new or recent events, possibly related to news articles or announcements

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "New."

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

xual

-0.80

ONSORED

-0.78

uca

-0.72

ILA

-0.69

ppe

-0.69

OPA

-0.68

cientious

-0.68

odox

-0.68

abet

-0.67

ickr

-0.67

POSITIVE LOGITS

 York

1.25

bies

1.21

 Zealand

1.20

bie

1.18

foundland

1.11

 Orleans

1.09

 Hampshire

1.09

 Yorker

0.96

 Jersey

0.93

 arrivals

0.91

Activations Density 0.066%

references to new or recent events, possibly related to news articles or announcements

occurrences of the word "New."

No Comments

No Known Activations