INDEX

Explanations

schedule-related information, particularly regarding operating hours and events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.8.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

 deriv

-0.66

founded

-0.66

 clone

-0.65

 Inher

-0.64

abulary

-0.63

 transpl

-0.62

 inherited

-0.62

ingen

-0.62

cule

-0.61

ĳå£«

-0.61

POSITIVE LOGITS

 Mondays

1.62

 noon

1.58

 Thurs

1.54

 Tues

1.51

 Saturdays

1.50

 midnight

1.49

 Fridays

1.49

 midday

1.41

 Sundays

1.40

 curfew

1.40

Activations Density 0.743%

schedule-related information, particularly regarding operating hours and events

No Comments

No Known Activations