INDEX

Explanations

sporting events or competitions related to playoff rounds

oai_token-act-pair · gpt-3.5-turbo

references to sports event stages, particularly finals and semifinals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

veh

-0.72

rians

-0.68

 directions

-0.66

rian

-0.63

Beer

-0.59

holding

-0.59

lying

-0.59

 liability

-0.58

 knowledge

-0.58

 appetite

-0.58

POSITIVE LOGITS

finals

1.26

final

0.90

bledon

0.88

é¾įåĸļå£«

0.88

 Finals

0.86

eteenth

0.86

nesday

0.85

poons

0.84

AFTA

0.84

kees

0.83

Activations Density 0.008%

sporting events or competitions related to playoff rounds

references to sports event stages, particularly finals and semifinals

No Comments

No Known Activations